此页面由 AI 自动翻译。查看英文原版
最后更新
Claude CodeCodexCursor
Luxonis 智能体工具包为你常用的编程智能体加载 Luxonis 上下文与技能,更快地基于 OAK 开发应用。
安装工具包

DepthAI Python API

最后更新
DepthAI Python API 可以在 Github luxonis/depthai-core 上找到。 以下是 Python API 的参考文档。
package

depthai

package
beta
Experimental APIs
package
filters
Parameters for filters
module
modelzoo
Model Zoo
package
package
module
utility
Utility functions
class
Timestamp
Timestamp structure
class
Point2f
Point2f structure  x and y coordinates that define a 2D point.
class
Point3f
Point3f structure  x,y,z coordinates that define a 3D point.
class
Point3fRGBA
Point3fRGBA structure  x,y,z coordinates and RGB color values that define a 3D point with color and alpha.
class
Point3d
Point3d structure  x,y,z coordinates that define a 3D point.
class
Quaterniond
Quaterniond structure  qx,qy,qz,qw coordinates that define a 3D point orientation.
class
Size2f
Size2f structure  width, height values define the size of the shape/frame
class
CameraBoardSocket
Which Camera socket to use.  AUTO denotes that the decision will be made by device  Members:    AUTO    CAM_A    CAM_B    CAM_C    CAM_D    VERTICAL    CAM_E    CAM_F    CAM_G    CAM_H    CBA : Experimental feature. This API might change or be removed in a future release.    RGB : **Deprecated:** Use CAM_A or address camera by name instead    LEFT : **Deprecated:** Use CAM_B or address camera by name instead    RIGHT : **Deprecated:** Use CAM_C or address camera by name instead    CENTER : **Deprecated:** Use CAM_A or address camera by name instead
class
HousingCoordinateSystem
Which Housing to use.  AUTO denotes that the decision will be made by device  Members:    CAM_A    CAM_B    CAM_C    CAM_D    CAM_E    CAM_F    CAM_G    CAM_H    CAM_I    CAM_J    FRONT_CAM_A    FRONT_CAM_B    FRONT_CAM_C    FRONT_CAM_D    FRONT_CAM_E    FRONT_CAM_F    FRONT_CAM_G    FRONT_CAM_H    FRONT_CAM_I    FRONT_CAM_J    VESA_A    VESA_B    VESA_C    VESA_D    VESA_E    VESA_F    VESA_G    VESA_H    VESA_I    VESA_J    IMU
class
ExternalFrameSyncRole
Which external frame sync role the device should have.  AUTO_DETECT denotes that the decision will be made by device. It will choose between MASTER and SLAVE.  Members:    AUTO_DETECT    MASTER    SLAVE
class
connectionInterface
Members:    USB    ETHERNET    WIFI
class
CameraSensorType
Camera sensor type  Members:    COLOR    MONO    TOF    THERMAL
class
CameraImageOrientation
Camera sensor image orientation / pixel readout. This exposes direct sensor settings. 90 or 270 degrees rotation is not available.  AUTO denotes that the decision will be made by device (e.g. on OAK-1/megaAI: ROTATE_180_DEG).  Members:    AUTO    NORMAL    HORIZONTAL_MIRROR    VERTICAL_FLIP    ROTATE_180_DEG
class
CameraSensorConfig
Sensor config
class
CameraFeatures
CameraFeatures structure  Characterizes detected cameras on board
class
MemoryInfo
MemoryInfo structure  Free, remaining and total memory stats
class
ChipTemperature
Chip temperature information.  Multiple temperature measurement points and their average
class
ChipTemperatureRVC4
Chip temperature information.  Multiple temperature measurement points and their average
class
CpuUsage
CpuUsage structure  Average usage in percent and time span of the average (since last query)
class
CameraModel
Projection model of a camera.  `Perspective`, `Fisheye` and `RadialDivision` are pinhole cameras whose distortion is applied on the normalized image plane. `Equirectangular` and `Cylindrical` are the surfaces panoramas are rendered onto; they carry no distortion coefficients, and their intrinsic matrix (fx, fy, cx, cy) maps the angular coordinates of a direction (x, y, z) in the camera frame to a pixel instead of the normalized image plane: - Equirectangular: u = fx * atan2(x, z) + cx, v = fy * asin(y / sqrt(x^2 + y^2 + z^2)) + cy - Cylindrical: u = fx * atan2(x, z) + cx, v = fy * y / sqrt(x^2 + z^2) + cy  so fx and fy are the radius of the sphere or cylinder in pixels, and (cx, cy) is the pixel the camera Z axis projects to.  Members:    Perspective    Fisheye    Equirectangular    RadialDivision    Cylindrical
class
StereoRectification
StereoRectification structure
class
Extrinsics
Extrinsics structure
class
MultiDeviceExtrinsics
A directed cross-device calibration edge.  The source coordinate system is identified by fromDeviceId/fromSocket. The destination coordinate system is identified by extrinsics.toDeviceId and extrinsics.toCameraSocket.
class
CameraInfo
CameraInfo structure
class
EepromData
EepromData structure  Contains the Calibration and Board data stored on device
class
ImuNoiseParameters
Allan-variance-derived IMU noise parameters.
class
ImuCalibrationParams
Complete IMU parameter payload: noise + per-sensor canonical affine calibration.
class
class
class
class
class
UsbSpeed
Get USB Speed  Members:    UNKNOWN    LOW    FULL    HIGH    SUPER    SUPER_PLUS
class
ProcessorType
Members:    LEON_CSS    LEON_MSS    CPU    DSP
class
DetectionNetworkType
Members:    YOLO    MOBILENET
class
LengthUnit
Measurement unit for depth and calibration data.  Members:    METER    CENTIMETER    MILLIMETER    INCH    FOOT    CUSTOM
class
AngleUnit
Measurement unit for angular quantities stored in radians.  Members:    RADIAN    DEGREE
class
YoloDecodingFamily
Members:    TLBR    v5AB    v3AB    R1AF
class
SerializationType
Members:    LIBNOP    JSON    JSON_MSGPACK
class
DetectionParserOptions
DetectionParserOptions  Specifies how to parse output of detection networks
class
RotatedRect
RotatedRect structure
class
Rect
Rect structure  x,y coordinates together with width and height that define a rectangle. Can be either normalized [0,1] or absolute representation.
class
StereoPair
Describes which camera sockets can be used for stereo and their baseline.
class
CameraExposureOffset
Members:    START    MIDDLE    END
class
Color
Color structure  r,g,b,a color values with values in range [0.0, 1.0]
class
Colormap
Camera sensor type  Members:    NONE    JET    TURBO    STEREO_JET    STEREO_TURBO
class
FrameEvent
Members:    NONE    READOUT_START    READOUT_END
class
class
Interpolation
Interpolation type  Members:    BILINEAR    BICUBIC    NEAREST_NEIGHBOR    BYPASS    DEFAULT    DEFAULT_DISPARITY_DEPTH
class
DeviceModelZoo
On device models, relevant for RVC4 platform  Members:    NEURAL_DEPTH_1248X780    NEURAL_DEPTH_1056X660    NEURAL_DEPTH_960X600    NEURAL_DEPTH_864X540    NEURAL_DEPTH_768X480    NEURAL_DEPTH_576X360    NEURAL_DEPTH_480X300    NEURAL_DEPTH_384X240    NEURAL_DEPTH_288X180    NEURAL_DEPTH_192X120    NEURAL_DEPTH_EXTRA_LARGE    NEURAL_DEPTH_LARGE    NEURAL_DEPTH_MEDIUM    NEURAL_DEPTH_SMALL    NEURAL_DEPTH_NANO
class
class
class
class
SpatialKeypointsList
List of spatial keypoints.  All `SpatialKeypoint::spatialCoordinates` values stored in this list are expressed in `unit` units. Mixed spatial units within a single list are not supported.
class
DatatypeEnum
Members:    ADatatype    Buffer    Transformable    ImgFrame    EncodedFrame    NNData    ImageManipConfig    CameraControl    ImgDetections    SpatialImgDetections    DetectionParserConfig    SegmentationParserConfig    SegmentationMask    SystemInformation    SystemInformationRVC4    SpatialLocationCalculatorConfig    SpatialLocationCalculatorData    EdgeDetectorConfig    AprilTagConfig    AprilTags    Tracklets    IMUData    StereoDepthConfig    GPUStereoConfig    FeatureTrackerConfig    ThermalConfig    ToFConfig    VppConfig    TrackedFeatures    BenchmarkReport    MessageGroup    TransformData    Odometry    PointCloudConfig    PointCloudData    ImageAlignConfig    AlignConfig    ImgAnnotations    MapData    RGBDData    PipelineEvent    PipelineState    ImageFiltersConfig    ToFDepthConfidenceFilterConfig    DynamicCalibrationControl    DynamicCalibrationResult    AutoCalibrationConfig    AutoCalibrationResult    CalibrationQuality    ImgDetectionsFilterConfig    Classifications    Keypoints    Clusters    Map2D    Lines    Predictions    FastSAMParserConfig    HRNetParserConfig    MLSDParserConfig    MPPalmDetectionParserConfig    PPTextDetectionParserConfig    RFDETRParserConfig    SCRFDParserConfig    SuperAnimalParserConfig    YuNetParserConfig    ClassificationSequenceParserConfig    MapOutputParserConfig    XFeatMonoParserConfig    XFeatStereoParserConfig    MultiDeviceCalibrationControl    MultiDeviceCalibrationResult    CoverageData
class
ADatatype
Abstract message
class
Buffer
Base message - buffer of binary data
class
class
Transformable
Interface for messages that carry image transformation metadata and can be remapped to another image transformation.
class
TransformableBuffer
Base message type for custom transformable messages.  This class combines Buffer storage with the Transformable interface and provides a virtual transformTo() entry point for host-side polymorphic dispatch. Python users should inherit from TransformableBuffer, not Transformable, when implementing custom messages that need transformation support.
class
AprilTagConfig
AprilTagConfig message.
class
AprilTag
AprilTag structure.
class
AprilTags
AprilTags message.
class
CameraControl
CameraControl message. Specifies various camera control commands like:  - Still capture  - Auto/manual focus  - Auto/manual white balance  - Auto/manual exposure  - Anti banding  - ...  By default the camera enables 3A, with auto-focus in `CONTINUOUS_VIDEO` mode, auto-white-balance in `AUTO` mode, and auto-exposure with anti-banding for 50Hz mains frequency.
class
class
EdgeDetectorConfig
EdgeDetectorConfig message. Carries sobel edge filter config.
class
FeatureTrackerConfig
FeatureTrackerConfig message. Carries config for feature tracking algorithm
class
ThermalConfig
ThermalConfig message. Currently unused.
class
class
class
ThermalAmbientParams
Ambient factors that affect the temperature measurement of a Thermal sensor.
class
ThermalGainMode
Thermal sensor gain mode. Use low gain in high energy environments.  Members:    LOW :     HIGH : 
class
ToFConfig
ToFConfig message. Carries config for feature tracking algorithm
class
ImageManipConfig
ImageManipConfig message. Specifies image manipulation options like:  - Crop  - Resize  - Warp  - ...
class
ImgDetections
ImgDetections message. Carries normalized detections and optional segmentation mask. The segmentation mask is stored as a single-channel INT8 2-d array, where the value represents the instance index in the list of detections. The value 255 is treated as a background pixel (no instance).
class
class
class
ImgTransformation
ImgTransformation struct. Holds information of how a ImgFrame or related message was transformed from their source. Useful for remapping from one ImgFrame to another.
class
class
class
IMUReportAccelerometer
Accelerometer  Units are [m/s^2]
class
IMUReportGyroscope
Gyroscope  Units are [rad/s]
class
IMUReportMagneticField
Magnetic field  Units are [uTesla]
class
IMUReportRotationVectorWAcc
Rotation Vector with Accuracy  Contains quaternion components: i,j,k,real
class
IMUPacket
IMU output  Contains combined output for all possible modes. Only the enabled outputs are populated.
class
IMUData
IMUData message. Carries normalized detection results
class
class
TensorInfo
TensorInfo structure
class
NNData
NNData message. Carries tensors and their metadata
class
NeuralDepthConfig
NeuralDepthConfig message.
class
GPUStereoConfig
Configuration for the GPUStereo node.
class
SpatialImgDetection
SpatialImgDetection structure  Contains image detection results together with spatial location data.
class
SpatialImgDetections
SpatialImgDetections message. Carries detection results together with spatial location data
class
DetectionParserConfig
Runtime thresholds for DetectionParser. Send to inputConfig to update subsequent detections. Model layout, labels and decoding family remain configured on the node.
class
class
SegmentationMask
SegmentationMask message.  Segmentation mask of an image is stored as a single-channel UINT8 array, where each value represents a class or instance index. The value 255 is treated as background pixels (no class/instance).
class
SpatialLocationCalculatorConfigThresholds
SpatialLocation configuration thresholds structure  Contains configuration data for lower and upper threshold in depth units (millimeter by default) for ROI. Values outside of threshold range will be ignored when calculating spatial coordinates from depth map.
class
SpatialLocationCalculatorAlgorithm
SpatialLocationCalculatorAlgorithm configuration modes  Contains calculation method used to obtain spatial locations.  Members:    AVERAGE    MEAN    MIN    MAX    MODE    MEDIAN
class
SpatialLocationCalculatorConfigData
SpatialLocation configuration data structure
class
SpatialLocationCalculatorConfig
Configuration for SpatialLocationCalculator.  Holds global parameters and optional per-ROI entries used to compute 3D spatial locations from a depth map.  Global parameters (defaults): - Lower depth threshold [mm]: 0 - Upper depth threshold [mm]: 65535 - Calculation algorithm: MEDIAN - Step size: AUTO - Keypoint radius [px]: 10 - Calculate spatial keypoints: true - Use segmentation for ImgDetections: true - Segmentation passthrough: true - Bounding box scale factor: 1.0  An optional list of per-ROI configurations is available via `config`. ROI settings override the corresponding global values where specified.
class
SpatialLocationCalculatorData
SpatialLocationCalculatorData message. Carries spatial information (X,Y,Z) and their configuration parameters
class
SpatialLocations
SpatialLocations structure  Contains configuration data, average depth for the calculated ROI on depth map. Together with spatial coordinates: x,y,z relative to the center of depth map. Units are in depth units (millimeter by default).
class
StereoDepthConfig
StereoDepthConfig message.
class
SystemInformation
SystemInformation message. Carries memory usage, cpu usage and chip temperatures.
class
SystemInformationRVC4
SystemInformation message Carries memory usage, cpu usage and chip temperatures.
class
TrackedFeature
TrackedFeature structure
class
TrackedFeatures
TrackedFeatures message. Carries position (X, Y) of tracked features and their ID.
class
Tracklet
Tracklet structure  Contains tracklets from object tracker output.
class
Tracklets
Tracklets message. Carries object tracking information.
class
BenchmarkReport
BenchmarkReport message.
class
PointCloudConfig
PointCloudConfig message. Carries point cloud output settings.
class
PointCloudData
PointCloudData message. Carries point cloud data.
class
PipelineEvent
Pipeline event message.
class
class
PipelineState
Pipeline event message.
class
TransformData
TransformData message. Carries transform in x,y,z,qx,qy,qz,qw format.
class
Odometry
Odometry message. Carries a pose and the linear velocity of the tracked body.  The pose is inherited from TransformData. Velocity is expressed in the same reference coordinate system as the pose translation and is measured in m/s.
class
ImageAlignConfig
ImageAlignConfig configuration structure
class
AlignConfig
AlignConfig configuration structure
class
class
class
PointsAnnotationType
Members:    UNKNOWN    POINTS    LINE_LOOP    LINE_STRIP    LINE_LIST
class
class
class
class
class
class
class
class
class
class
RGBDData
RGBD message. Carries RGB and Depth frames. Frames can be either of type ImgFrame or EncodedFrame.
class
MapData
MapData message. Carries grid map data and minX/minY messages to help place it in 3D space.
class
VppConfig
VppConfig message. Carries config for Virtual Projection Pattern algorithm
class
class
class
class
class
class
class
class
class
AutoCalibrationConfig
AutoCalibrationConfig message. Carries configuration for the automatic camera calibration algorithm. Defines parameters for periodic or one-time recalibration of the camera sensors.
class
class
ModelType
Neural network model type  Members:    BLOB    SUPERBLOB    DLC    NNARCHIVE    OTHER
class
LogLevel
Members:    TRACE    DEBUG    INFO    WARN    ERR    CRITICAL    OFF
class
class
Version
Version structure
class
MessageQueue
Thread safe queue to send messages between nodes
class
OpenVINO
Support for basic OpenVINO related actions like version identification of neural network blobs,...
class
class
class
class
class
class
class
class
class
class
class
class
ImgResizeMode
Members:    CROP    STRETCH    LETTERBOX
class
Node
Abstract Node
class
Properties
Base Properties structure
class
class
class
class
class
class
class
ColorCameraProperties
Specify properties for ColorCamera such as camera ID, ...
class
MonoCameraProperties
Specify properties for MonoCamera such as camera ID, ...
class
StereoDepthProperties
Specify properties for StereoDepth
class
NeuralNetworkProperties
Specify properties for NeuralNetwork such as blob path, ...
class
VideoEncoderProperties
Specify properties for VideoEncoder such as profile, bitrate, ...
class
ImageManipProperties
Specify properties for ImageManip
class
WarpProperties
Specify properties for Warp
class
SPIOutProperties
Specify properties for SPIOut node
class
SPIInProperties
Properties for SPIIn node
class
SystemLoggerProperties
SystemLoggerProperties structure
class
ScriptProperties
Specify ScriptProperties options such as script uri, script name, ...
class
SpatialLocationCalculatorProperties
Specify properties for SpatialLocationCalculator
class
SpatialDetectionNetworkProperties
Specify properties for SpatialDetectionNetwork
class
TrackerType
Members:    SHORT_TERM_KCF : Kernelized Correlation Filter tracking    SHORT_TERM_IMAGELESS : Short term tracking without using image data    ZERO_TERM_IMAGELESS : Ability to track the objects without accessing image data.    ZERO_TERM_COLOR_HISTOGRAM : Tracking using image data too.
class
TrackerIdAssignmentPolicy
Members:    UNIQUE_ID    SMALLEST_ID
class
ObjectTrackerProperties
Specify properties for ObjectTracker
class
IMUSensor
Available IMU sensors. More details about each sensor can be found in the datasheet:  https://www.ceva-dsp.com/wp-content/uploads/2019/10/BNO080_085-Datasheet.pdf  Members:    ACCELEROMETER_RAW : Section 2.1.1  Raw accelerometer measurement in the sensor-native frame. No IMU extrinsics or affine calibration are applied. Units are [m/s^2]  @note Prior firmware versions incorrectly delivered frame-aligned data on this stream (equivalent to what is now ACCELEROMETER_UNCALIBRATED). This stream now correctly provides the unprocessed sensor output.    ACCELEROMETER_UNCALIBRATED : DepthAI synthetic accelerometer stream.  Acceleration of the device including gravity, aligned to the DepthAI IMU frame without the stored affine calibration applied. Units are [m/s^2]    ACCELEROMETER_CALIBRATED : Section 2.1.1  Acceleration of the device including gravity, aligned to the DepthAI IMU frame and corrected with the stored affine calibration. Units are [m/s^2]    ACCELEROMETER : Deprecated: use ACCELEROMETER_CALIBRATED    LINEAR_ACCELERATION : Deprecated: calibration is incorrect for this gravity-stripped output; use ACCELEROMETER_CALIBRATED and subtract gravity on the host    GRAVITY : Deprecated: calibration is incorrect for this gravity-only output; use ACCELEROMETER_CALIBRATED and estimate gravity on the host    GYROSCOPE_RAW : Section 2.1.2  Raw gyroscope measurement in the sensor-native frame. DepthAI does not apply IMU extrinsics or affine calibration on this stream. Units are [rad/s]    GYROSCOPE_CALIBRATED : Section 2.1.2  Angular velocity aligned to the DepthAI IMU frame and corrected with the stored affine calibration. Units are [rad/s]    GYROSCOPE_UNCALIBRATED : Section 2.1.2  Angular velocity aligned to the DepthAI IMU frame without the stored affine calibration applied. Units are [rad/s]    MAGNETOMETER_RAW : Section 2.1.3  Raw magnetometer measurement in the sensor-native frame. DepthAI does not apply IMU extrinsics on this stream. Units are [uTesla]    MAGNETOMETER_CALIBRATED : Section 2.1.3  Magnetic field measurement aligned to the DepthAI IMU frame. Units are [uTesla]    MAGNETOMETER_UNCALIBRATED : Section 2.1.3  Magnetic field measurement aligned to the DepthAI IMU frame without hard-iron offset applied. Units are [uTesla]    ROTATION_VECTOR : Section 2.2  The rotation vector provides an orientation output that is expressed as a quaternion referenced to magnetic north and gravity. It is produced by fusing the outputs of the accelerometer, gyroscope and magnetometer. The rotation vector is the most accurate orientation estimate available. The magnetometer provides correction in yaw to reduce drift and the gyroscope enables the most responsive performance.    GAME_ROTATION_VECTOR : Section 2.2  The game rotation vector is an orientation output that is expressed as a quaternion with no specific reference for heading, while roll and pitch are referenced against gravity. It is produced by fusing the outputs of the accelerometer and the gyroscope (i.e. no magnetometer). The game rotation vector does not use the magnetometer to correct the gyroscopes drift in yaw. This is a deliberate omission (as specified by Google) to allow gaming applications to use a smoother representation of the orientation without the jumps that an instantaneous correction provided by a magnetic field update could provide. Long term the output will likely drift in yaw due to the characteristics of gyroscopes, but this is seen as preferable for this output versus a corrected output.    GEOMAGNETIC_ROTATION_VECTOR : Section 2.2  The geomagnetic rotation vector is an orientation output that is expressed as a quaternion referenced to magnetic north and gravity. It is produced by fusing the outputs of the accelerometer and magnetometer. The gyroscope is specifically excluded in order to produce a rotation vector output using less power than is required to produce the rotation vector of section 2.2.4. The consequences of removing the gyroscope are: Less responsive output since the highly dynamic outputs of the gyroscope are not used More errors in the presence of varying magnetic fields.    ARVR_STABILIZED_ROTATION_VECTOR : Section 2.2  Estimates of the magnetic field and the roll/pitch of the device can create a potential correction in the rotation vector produced. For applications (typically augmented or virtual reality applications) where a sudden jump can be disturbing, the output is adjusted to prevent these jumps in a manner that takes account of the velocity of the sensor system.    ARVR_STABILIZED_GAME_ROTATION_VECTOR : Section 2.2  While the magnetometer is removed from the calculation of the game rotation vector, the accelerometer itself can create a potential correction in the rotation vector produced (i.e. the estimate of gravity changes). For applications (typically augmented or virtual reality applications) where a sudden jump can be disturbing, the output is adjusted to prevent these jumps in a manner that takes account of the velocity of the sensor system. This process is called AR/VR stabilization.
class
class
class
EdgeDetectorProperties
Specify properties for EdgeDetector
class
FeatureTrackerProperties
Specify properties for FeatureTracker
class
AprilTagProperties
Specify properties for AprilTag
class
DetectionParserProperties
Specify properties for DetectionParser
class
SegmentationParserProperties
Specify properties for SegmentationParser  @property labels Vector of class labels associated with the segmentation mask. The label at index $i$ in the `labels` vector corresponds to the value $i$-th channel in the segmentation mask data array.  Parameter ``networkOutputName``:     Name of the output tensor from the neural network to parse. If empty, the     first output will be used.  Parameter ``classesInOneLayer``:     If true, assumes that the segmentation classes are already encoded in a     single layer as integer values. If false, an argmax operation is performed     across multiple channels.  Parameter ``backgroundClass``:     If true, the first class (index 0) is considered as background.
class
UVCProperties
Properties for UVC node
class
ThermalProperties
Specify properties for Thermal
class
ToFProperties
Specify properties for ToF
class
PointCloudProperties
Specify properties for PointCloud
class
SyncProperties
Specify properties for Sync.
class
MessageDemuxProperties
Specify properties for MessageDemux.
class
class
class
class
class
ImageAlignProperties
Specify properties for ImageAlign
class
AlignProperties
Specify properties for Align
class
class
NeuralDepthProperties
Specify properties for NeuralDepth
class
class
VppProperties
Specify properties for Vpp node
class
GateProperties
Specify properties for Gate.
class
class
class
DynamicCalibrationProperties
Specify properties for Dynamic calibration.
class
class
Asset
Asset is identified with string key and can store arbitrary binary data
class
AssetManager
AssetManager can store assets and serialize
class
GlobalProperties
Specify properties which apply for whole pipeline
class
DeviceProperties
Specify properties which apply for a device
class
RecordConfig
Configuration for recording and replaying messages
class
class
DeviceState
State of a device that is part of a running pipeline.  Members:    RUNNING    DISCONNECTED    RECONNECTING    FAILED
class
NodesStateApi
pipeline.getState().nodes({nodeId1}).summary() -> std::unordered_map<std::string, TimingStats>; pipeline.getState().nodes({nodeId1}).detailed() -> std::unordered_map<std::string, NodeState>; pipeline.getState().nodes(nodeId1).detailed() -> NodeState; pipeline.getState().nodes({nodeId1}).outputs() -> std::unordered_map<std::string, TimingStats>; pipeline.getState().nodes({nodeId1}).outputs({outputName1}) -> std::unordered_map<std::string, TimingStats>; pipeline.getState().nodes({nodeId1}).outputs(outputName) -> TimingStats; pipeline.getState().nodes({nodeId1}).events(); pipeline.getState().nodes({nodeId1}).inputs() -> std::unordered_map<std::string, QueueState>; pipeline.getState().nodes({nodeId1}).inputs({inputName1}) -> std::unordered_map<std::string, QueueState>; pipeline.getState().nodes({nodeId1}).inputs(inputName) -> QueueState; pipeline.getState().nodes({nodeId1}).otherStats() -> std::unordered_map<std::string, TimingStats>; pipeline.getState().nodes({nodeId1}).otherStats({statName1}) -> std::unordered_map<std::string, TimingStats>; pipeline.getState().nodes({nodeId1}).outputs(statName) -> TimingStats;
class
class
class
DeviceInfo
Describes a connected device
class
class
XLinkDeviceState
Members:    X_LINK_ANY_STATE    X_LINK_BOOTED    X_LINK_UNBOOTED    X_LINK_BOOTLOADER    X_LINK_FLASH_BOOTED    X_LINK_BOOTED_NON_EXCLUSIVE    X_LINK_GATE    X_LINK_GATE_BOOTED    X_LINK_GATE_SETUP
class
XLinkProtocol
Members:    X_LINK_USB_VSC    X_LINK_USB_CDC    X_LINK_PCIE    X_LINK_IPC    X_LINK_TCP_IP    X_LINK_LOCAL_SHDMEM    X_LINK_TCP_IP_OR_LOCAL_SHDMEM    X_LINK_USB_EP    X_LINK_NMB_OF_PROTOCOLS    X_LINK_ANY_PROTOCOL
class
XLinkPlatform
Members:    X_LINK_ANY_PLATFORM    X_LINK_MYRIAD_2    X_LINK_MYRIAD_X    X_LINK_RVC3    X_LINK_RVC4
class
XLinkError_t
Members:    X_LINK_SUCCESS    X_LINK_ALREADY_OPEN    X_LINK_COMMUNICATION_NOT_OPEN    X_LINK_COMMUNICATION_FAIL    X_LINK_COMMUNICATION_UNKNOWN_ERROR    X_LINK_DEVICE_NOT_FOUND    X_LINK_TIMEOUT    X_LINK_ERROR    X_LINK_OUT_OF_MEMORY    X_LINK_INSUFFICIENT_PERMISSIONS    X_LINK_DEVICE_ALREADY_IN_USE    X_LINK_NOT_IMPLEMENTED    X_LINK_INIT_USB_ERROR    X_LINK_INIT_TCP_IP_ERROR    X_LINK_INIT_PCIE_ERROR
class
XLinkConnection
Represents connection between host and device over XLink protocol
exception
exception
exception
class
Platform
Hardware platform type  Members:    RVC2 :     RVC3 :     RVC4 : 
class
CrashDump
Base class for platform-specific crash dumps  Crash dumps are serialized as tar files with the following structure: - crash_dump.tar.gz - metadata.json (basic crash information - depthai specific) - extra.json (user-defined extra crashdump information) - platform specific files...
class
class
class
class
Device
Represents the DepthAI device with the methods to interact with it. Implements the host-side queues to connect with XLinkIn and XLinkOut nodes
class
HealthCheckConfig
Configures which device health-check steps should run.
class
HealthCheckIssue
Health check issue, which contains the details of the issue
class
HealthCheckMetrics
Device health-check results.
class
HealthCheckIssueType
Health check issue type  Members:    Warning :     Error : 
class
HealthCheckIssueStage
Health check issue stage  Members:    Connection :     DeviceAvailability :     UsbGeneration :     Bandwidth :     CameraFunctionality :     CameraCalibration :     ImuFunctionality :     ImuCalibration :     PowerSupply : 
class
UsbGeneration
USB generation reported by the device health check.  Members:    UNKNOWN :     USB_1_0 :     USB_1_1 :     USB_2_0 :     USB_3_0 :     USB_3_1 : 
class
HealthCheckResult
Health check result reported by the device health check.  Members:    NOT_RUN :     PASS :     FAIL : 
class
class
exception
class
DeviceBootloader
Represents the DepthAI bootloader with the methods to interact with it.
class
class
CBACalibrationHandler
CBACalibrationHandler is a single-camera calibration interface for calibration data read from a CBA EEPROM.  It preserves the underlying EepromData layout, including the cameraData map, but camera-specific APIs use CameraBoardSocket::CBA as the logical single-camera data key without requiring the caller to pass it again.  .. warning::     Experimental feature. This API might change or be removed in a future     release.
class
class
class
class
class
SendSnapCallbackStatus
Members:    SUCCESS    FILE_BATCH_PREPARATION_FAILED    GROUP_CONTAINS_REJECTED_FILES    FILE_UPLOAD_FAILED    SEND_EVENT_FAILED    EVENT_REJECTED
class
class
class
ImageFiltersPresetMode
Members:    TOF_LOW_RANGE    TOF_MID_RANGE    TOF_HIGH_RANGE
function
function
function
downloadModelsFromZoo(path: os.PathLike, cacheDirectory: os.PathLike = '', apiKey: str = '', progressFormat: str = 'none') -> bool: bool
Helper function allowing one to download all models specified in yaml files in the given path and store them in the cache directory  Parameter ``path:``:     Path to the directory containing yaml files  Parameter ``cacheDirectory:``:     Cache directory where the cached models are stored, default is "". If     cacheDirectory is set to "", this function checks the DEPTHAI_ZOO_CACHE_PATH     environment variable and uses that if set, otherwise the default is used     (see getDefaultCachePath).  Parameter ``apiKey:``:     API key for the model zoo, default is "". If apiKey is set to "", this     function checks the DEPTHAI_ZOO_API_KEY environment variable and uses that     if set. Otherwise, no API key is used.  Parameter ``progressFormat:``:     Format to use for progress output (possible values: pretty, json, none),     default is "pretty"  Returns:     bool: True if all models were downloaded successfully, false otherwise
function
getModelFromZoo(modelDescription: NNModelDescription, useCached: bool = True, cacheDirectory: os.PathLike = '', apiKey: str = '', progressFormat: str = 'none') -> os.PathLike: os.PathLike
Get model from model zoo  Parameter ``modelDescription:``:     Model description  Parameter ``useCached:``:     Use cached model if present, default is true  Parameter ``cacheDirectory:``:     Cache directory where the cached models are stored, default is "". If     cacheDirectory is set to "", this function checks the DEPTHAI_ZOO_CACHE_PATH     environment variable and uses that if set, otherwise the default value is     used (see getDefaultCachePath).  Parameter ``apiKey:``:     API key for the model zoo, default is "". If apiKey is set to "", this     function checks the DEPTHAI_ZOO_API_KEY environment variable and uses that     if set. Otherwise, no API key is used.  Parameter ``progressFormat:``:     Format to use for progress output (possible values: pretty, json, none),     default is "pretty"  Returns:     std::filesystem::path: Path to the model in cache
function
function
platform2string(arg0: Platform) -> str: str
Convert Platform enum to string  Parameter ``platform``:     Platform enum  Returns:     std::string String representation of Platform
function
readModelType(modelPath: os.PathLike) -> ModelType: ModelType
Read model type from model path  Parameter ``modelPath``:     Path to model  Returns:     ModelType
function
string2platform(arg0: str) -> Platform: Platform
Convert string to Platform enum  Parameter ``platform``:     String representation of Platform  Returns:     Platform Platform enum
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
package

depthai.beta

module
node
Experimental nodes
class
Classifications
Classifications message. Carries classification class names and their corresponding scores.  The classes and scores vectors are index-aligned. Parsers emit them sorted in descending order of score, so the first entry is the most probable class.
class
Cluster
Cluster of 2D points. Serialized value type contained by the Clusters message.
class
Clusters
Clusters message. Carries clusters of 2D points, each cluster with an integer label.  Parsers emit clusters with sequential labels starting at 0 and point image coordinates normalized to [0, 1]. Clusters may be empty, e.g. lanes without enough detected points.
class
Keypoints
Keypoints message. Streamable wrapper around the native dai::KeypointsList, carrying 2D or 3D keypoints together with optional skeleton edges connecting them.  Keypoint image coordinates are normalized to [0, 1] by the keypoint parsers. 2D keypoints carry a z coordinate of 0.
class
Line
Detected line segment. Serialized value type contained by the Lines message.
class
Lines
Lines message. Carries detected line segments, each with a start point, an end point and a confidence score.  Parsers emit line point image coordinates normalized to [0, 1] and confidences clipped to [0, 1]. The message may carry no lines when nothing passes the detection thresholds.
class
Map2D
Map2D message. Carries a dense 2D map of 32-bit floats, such as a depth map, a density map or a heat map, together with image transformation metadata.  The map values are stored row-major in the buffer payload; the map dimensions are carried in the serialized metadata.
class
Prediction
Single predicted value. Serialized value type contained by the Predictions message.
class
Predictions
Predictions message. Carries the predicted value(s) of a regression model in the order the model emitted them.  The message may carry no predictions when the parsed tensor is empty.
class
MultiDeviceCalibrationControl
One-shot lifecycle commands for the MultiDeviceCalibration node.  Configuration belongs to the node and must be set before start. The control message intentionally contains no performance or device-mutation commands.
class
MultiDeviceCalibrationResult
Final result of running multi-device calibration.  Includes: - the estimated cross-device calibration graph (only when the run passed) - metrics evaluating the reliability of the estimate and the quality of the data used to compute it - a human-readable description of why a run did not pass  The calibration graph is a snapshot and is never applied to a device or pipeline by the node. Use getHandler() to resolve it or store it on a pipeline with Pipeline::setMultiDeviceCalibration.
class
ClassificationSequenceParserConfig
Runtime configuration for ClassificationSequenceParser.
class
FastSAMParserConfig
Runtime configuration for FastSAMParser.
class
HRNetParserConfig
Runtime configuration for HRNetParser.
class
MLSDParserConfig
Runtime configuration for MLSDParser.
class
MPPalmDetectionParserConfig
Runtime configuration for MPPalmDetectionParser.
class
MapOutputParserConfig
Runtime configuration for MapOutputParser.
class
PPTextDetectionParserConfig
Runtime configuration for PPTextDetectionParser.
class
RFDETRParserConfig
Runtime configuration for RFDETRParser.
class
SCRFDParserConfig
Runtime configuration for SCRFDParser.
class
SuperAnimalParserConfig
Runtime configuration for SuperAnimalParser.
class
XFeatMonoParserConfig
Runtime configuration for XFeatMonoParser.
class
XFeatStereoParserConfig
Runtime configuration for XFeatStereoParser.
class
YuNetParserConfig
Runtime configuration for YuNetParser.
class
class
class
class
class
class
class
class
class
class
class
class
class
StitchingProperties
Serializable properties for the Stitching node.
class
class
class
class
MultiDeviceCalibrationHandler
Resolves cross-device calibration edges into a common origin for each connected component.  The input graph is a forest. Every edge endpoint must be a device's local calibration origin. The component origin is selected automatically as the lowest (device ID, socket) coordinate-system pair.
module

depthai.beta.node

class
ToFStereoFusion
Experimental node that fuses aligned ToF and neural stereo-depth measurements.  The node configures its internal ToF, neural-depth, alignment, synchronization, and fusion-network stages when built from a left and right camera.  @note This node is supported on RVC4 devices only. Creating it for an RVC2 device throws an exception.
class
ClassificationParser
ClassificationParser node. Parses the raw output of a classification neural network into a dai::beta::Classifications message with class names and scores sorted in descending order of score.  The parser consumes a single output tensor. When the incoming NNData contains exactly one tensor, it is selected automatically; otherwise the output layer name must be configured explicitly or through an NNArchive head. Raw scores are dequantized and flattened; when the model output is not already softmaxed, the parser applies softmax to convert the scores to probabilities.
class
ClassificationSequenceParser
ClassificationSequenceParser node. Parses the raw output of a classification sequence neural network into a dai::beta::Classifications message with class names and scores ordered by their position in the sequence.  The model predicts the classes multiple times and returns a list of predicted classes, where each item corresponds to the relative step in the sequence. In addition to time series classification, this parser can also be used for text recognition models where words can be interpreted as a sequence of characters (classes).  The parser consumes a single output tensor of shape (sequenceLength, nClasses), (1, sequenceLength, nClasses) or (sequenceLength, nClasses, 1). When the incoming NNData contains exactly one tensor, it is selected automatically; otherwise the output layer name must be configured explicitly or through an NNArchive head. Raw scores are dequantized; when the model output is not already softmaxed, the parser applies softmax along each sequence step to convert the scores to probabilities.
class
EmbeddingsParser
EmbeddingsParser node. Validates the raw output of an embeddings neural network model head and forwards it unchanged as a dai::NNData message.  The parser expects a single output tensor carrying the embedding vector. When the output layer name is left unconfigured, every incoming NNData must contain exactly one tensor; otherwise the message is rejected. The message itself is forwarded without modification, so all tensors, sequence number, timestamps, and image transformation metadata are preserved.
class
FastSAMParser
FastSAMParser node. Parses the output of the FastSAM segmentation model (https://github.com/CASIA-IVA-Lab/FastSAM) into a dai::SegmentationMask message where each pixel holds the index of the instance it belongs to and 255 marks background.  The parser consumes the model's YOLO detection outputs (NCHW tensors of shape (1, numClasses + 5, gridH, gridW), sorted by layer name and decoded anchorless with strides 8/16/32), the per-head mask-coefficient outputs (NCHW tensors of shape (1, numPrototypes, gridH, gridW), sorted by layer name) and the prototype masks output (NCHW tensor of shape (1, numPrototypes, protoH, protoW)). The model input size is derived from the first (stride-8) YOLO output's grid times 8; the number of prototypes from the protos tensor's channel count. Boxes pass confidence filtering and non-maximum suppression, boxes within 20 pixels of the image border are snapped to it, and a box overlapping the full image with IoU > 0.9 is replaced by the full-image box. Each kept detection's mask is combined from the prototypes, resized to the model input size with nearest-neighbor interpolation, cropped to its box and binarized with the mask confidence threshold.  The prompt selects the emitted instances: "everything" keeps all detections (later, lower-confidence instances overwrite earlier ones on overlapping pixels), "bbox" keeps the single mask with the highest IoU against the prompt bounding box, and "point" combines the masks containing the prompt point (added for point label 1, subtracted for 0). With no detections, a fully-background mask is emitted.
class
HRNetParser
HRNetParser node. Parses the heatmap output of an HRNet pose estimation neural network into a dai::beta::Keypoints message. The decoding is inspired by https://github.com/ibaiGorordo/ONNX-HRNET-Human-Pose-Estimation.  The parser consumes a single output tensor. When the incoming NNData contains exactly one tensor, it is selected automatically; otherwise the output layer name must be configured explicitly or through an NNArchive head. The tensor is read in NCHW orientation regardless of its stored order; after squeezing a leading batch dimension of 1 it must be a 3D tensor of shape (numKeypoints, height, width). The number of keypoints and the heatmap size are derived from the tensor shape. Per heatmap, the keypoint is the position of the maximum value normalized by the heatmap size and the keypoint's score is the maximum value clipped to [0, 1]. Keypoints with a score below the score threshold are dropped and the skeleton edges are remapped to the kept keypoints.
class
ImageOutputParser
ImageOutputParser node. Parses the output of image-to-image models (e.g. DnCNN3, zero-dce) where the output is a modified image (denoised, enhanced etc.) into a dai::ImgFrame message.  The parser consumes a single output tensor. When the incoming NNData contains exactly one tensor, it is selected automatically; otherwise the output layer name must be configured explicitly or through an NNArchive head. The tensor is read in its stored order; after squeezing a leading batch dimension of 1 it must be a 3D image tensor in CHW or HWC orientation, with the channel dimension equal to 1 (grayscale) or 3 (color). All dimensions are derived from the runtime tensor descriptor. The values are min-max normalized and scaled to the [0, 255] 8-bit range.  A grayscale image is emitted as a GRAY8 frame. A color image is emitted as a BGR888p frame when the pipeline's default device platform is RVC2 and as a BGR888i frame otherwise, including in a device-less pipeline. The model output is treated as RGB and converted to BGR unless the BGR-output flag marks it as already BGR.
class
ImgDetectionsFilter
Experimental node for filtering image detections.
class
KeypointParser
KeypointParser node. Parses the raw output of a 2D or 3D keypoints neural network into a dai::beta::Keypoints message.  The parser consumes a single output tensor. When the incoming NNData contains exactly one tensor, it is selected automatically; otherwise the output layer name must be configured explicitly or through an NNArchive head. The number of keypoints must be configured before the pipeline starts. The number of coordinates per keypoint (2 or 3) is derived from the tensor size and the configured number of keypoints. Keypoint coordinates are divided by the configured scale factor and clipped to [0, 1].
class
LaneDetectionParser
LaneDetectionParser node. Parses the output of an Ultra-Fast-Lane-Detection (UFLD) neural network, e.g. the CULane and TuSimple variants, into a dai::beta::Clusters message with one cluster of normalized points per lane, including empty clusters for lanes without enough detected points.  The parser consumes a single output tensor. When the incoming NNData contains exactly one tensor, it is selected automatically; otherwise the output layer name must be configured explicitly or through an NNArchive head. The tensor is read in its stored order and must be a 4D tensor of shape (batch, gridingNum + 1, clsNumPerLane, numLanes); the first batch entry is decoded. The row anchors, griding number and number of points per lane must be configured before the pipeline starts, either explicitly or through an NNArchive head. The input size must also be configured before the pipeline starts: building from a full NNArchive derives it from the model input's declared shape and layout (NHWC or NCHW), while building from a specific head requires setInputSize() because a head carries no model input metadata.
class
MapOutputParser
MapOutputParser node. Parses the output of models that produce map outputs, such as depth maps (e.g. DepthAnything), density maps (e.g. DM-Count), heat maps, and similar, into a dai::beta::Map2D message.  The parser consumes a single output tensor. When the incoming NNData contains exactly one tensor, it is selected automatically; otherwise the output layer name must be configured explicitly or through an NNArchive head. The tensor is read in its stored order; leading dimensions of 1 are squeezed and the tensor must then be a 2D HW map, or a 3D HWN map with a singleton trailing dimension that is squeezed as well. All map dimensions are derived from the runtime tensor descriptor.  When min-max scaling is enabled, the map values are scaled to the [0, 1] range; a constant map is left unchanged.
class
MLSDParser
MLSDParser node. Parses the output of the M-LSD line segment detection model into a dai::beta::Lines message with the detected lines and their confidence scores, ordered by descending score.  The parser consumes two output tensors that must be configured before the pipeline starts, either explicitly or through an NNArchive head: the tpMap tensor, read in NCHW orientation as a 4D tensor of shape (batch, channels, height, width) whose channels 1 to 4 hold the line displacement maps of the first batch entry, and the heat tensor, flattened to one score per (height, width) grid position. The topK highest-scoring grid positions are decoded into candidate lines and kept when their score and length are strictly above the score and distance thresholds. Ties between equal heat scores are ordered following numpy's portable argpartition/argsort semantics. The emitted line coordinates are normalized by the model input size, which defaults to 512x512 (the input size of all known M-LSD models, hard-coded by the source parser); building from a full NNArchive derives it from the model input's declared shape and layout (NHWC or NCHW), and setInputSize() overrides it.
class
MPPalmDetectionParser
MPPalmDetectionParser node. Parses the output of the MediaPipe palm detection model into a dai::ImgDetections message containing the rotated bounding boxes, labels and confidence scores of the detected hands. The decoding is based on https://github.com/geaxgx/depthai_hand_tracker (MIT License).  The parser consumes two output tensors and identifies them by their last dimension: the tensor with the larger last dimension holds the raw bounding boxes and is reshaped to (numAnchors, 18) rows of bounding box center/size plus 7 palm keypoint coordinate pairs; the tensor with the smaller last dimension holds the raw scores and is flattened to (numAnchors,). The scores are passed through a sigmoid and filtered with the confidence threshold, the kept rows are decoded against the model's SSD anchors generated from the configured scale (the model input size), converted to rectangles rotated to align the wrist to middle- finger direction with the rectangle's y-axis and expanded to squares, and non- maximum suppression keeps at most the configured maximum number of detections. The emitted bounding boxes are normalized to [0, 1].
class
MultiDeviceCalibration
Estimates metric cross-device calibration from synchronized camera images.  The node is host-only and one-shot. Configuration is supplied before the `start` control command; the node emits a pure-data result and enters its completed state. A `reset` command clears the cycle and permits another run.
class
PPTextDetectionParser
PPTextDetectionParser node. Parses the output of the PaddlePaddle OCR text detection model into a dai::ImgDetections message containing the rotated bounding boxes and confidence scores of the detected text.  The parser consumes a single probability-map output tensor of shape (1, 1, H, W) or (1, H, W, 1). The map is thresholded with the mask threshold into a binary text mask, the mask is dilated and its contours become rotated-rectangle candidates; when more contours than the maximum number of detections remain, the largest by area are kept. Rectangles smaller than 8 pixels on their smaller side are dropped, each candidate is scored with the mean probability inside its (slightly shrunk) corner polygon, candidates scoring below the confidence threshold are dropped, and the kept rectangles are expanded by sqrt(2) in both dimensions. The emitted bounding boxes are normalized to [0, 1] with angles in degrees rounded to whole numbers; the detections carry no labels.
class
RegressionParser
RegressionParser node. Parses the output of a model with regression output (e.g. age-gender) into a dai::beta::Predictions message with the predicted value(s) in the order the model emitted them.  The parser consumes a single output tensor. When the incoming NNData contains exactly one tensor, it is selected automatically; otherwise the output layer name must be configured explicitly or through an NNArchive head. The tensor is dequantized and all its singleton dimensions are squeezed; the remaining values become the predictions, so any tensor with at most one non-singleton dimension is accepted regardless of rank (for example (1, 1, 1, 3), (1, 1) or (1,)) and an empty tensor yields a message with no predictions. A tensor with more than one non-singleton dimension after squeezing is rejected.
class
RFDETRParser
RFDETRParser node. Parses the output of RF-DETR object detection models (https://github.com/roboflow/rf-detr) into a dai::ImgDetections message containing the bounding boxes, labels, confidence scores and, in segmentation mode, an instance segmentation mask, everything normalized to [0, 1].  The parser consumes 2 output tensors for detection (boxes, class logits) or 3 for instance segmentation (boxes, class logits, mask logits), in that order. When no output layer names are configured, all layer names of the incoming NNData are used in their reported order. The boxes tensor squeezes to (N, 4) with normalized (xCenter, yCenter, width, height) boxes, the logits tensor is (1, N, C) and the mask logits tensor squeezes to (N, maskHeight, maskWidth). Class probabilities are the sigmoid of the logits; per query the maximum probability is the score and its class the label. Detections are ordered by descending score, truncated to the maximum number of detections and kept when their score is strictly greater than the confidence threshold.  In segmentation mode at most 255 instances fit into the mask, so the truncation is additionally capped at 255. Each detection's mask logits are passed through a sigmoid, cropped to its bounding box, binarized with the mask confidence threshold and resized to the model input size with nearest-neighbor interpolation; the pixels not claimed by an earlier (higher-scoring) detection receive the detection's index, with 255 marking background.
class
SCRFDParser
SCRFDParser node. Parses the output of SCRFD detection models (e.g. SCRFD face and person detection) into a dai::ImgDetections message containing the bounding boxes, labels, confidence scores and 5 keypoints per detected object, everything normalized to [0, 1].  The parser consumes three output tensors per configured feature stride, named score_{stride}, bbox_{stride} and kps_{stride}. The score tensor is flattened, the bbox tensor is paired 4 values per score (left, top, right, bottom distances from the anchor center) and the kps tensor 10 values per score (5 keypoint coordinate pairs), accepting both batched (1, N, C) and unbatched (N, C) tensors. Scores greater than or equal to the confidence threshold (inclusive) are kept, decoded against the anchor centers derived from the input size, the stride and the number of anchors, sorted by descending score and suppressed with the original SCRFD non-maximum suppression (+1 offset box areas, overlaps at most the IoU threshold survive). The anchor centers are cached across messages and refreshed when the input size, feature strides or number of anchors change.
class
SuperAnimalParser
SuperAnimalParser node. Parses the heatmap output of the SuperAnimal landmark neural network into a dai::beta::Keypoints message.  The parser consumes a single output tensor. When the incoming NNData contains exactly one tensor, it is selected automatically; otherwise the output layer name must be configured explicitly or through an NNArchive head. The tensor is read in its stored order and must be a 4D tensor of shape (batch, height, width, numKeypoints) with a batch size of exactly 1. The number of keypoints and the heatmap size are derived from the tensor shape; the configured number of keypoints is informational only and does not affect the decoding. Per keypoint, the keypoint is the position of the maximum heatmap value with a 0.5-pixel center offset, mapped to input-image pixels and normalized by the configured scale factor without clipping, and the keypoint's score is the heatmap value at that position, which must lie in [0, 1]. Keypoints with a score strictly below the score threshold are dropped and the skeleton edges are remapped to the kept keypoints.
class
Stitching
Stitching node. Combines N time-synced image streams into a single stitched image.  The node runs on the host by default and can run on an RVC4 device when selected with `setRunOnHost(false)`. Host execution requires depthai-core OpenCV support. Inputs are fixed at build() time and synced by an internal Sync subnode that follows the node's execution side, so host-mode sources may come from different devices. Two independent stitching modes are available:  - `Mode::PANORAMA` wraps OpenCV's cv::Stitcher and registers the images from their content, so no calibration is needed, but the cameras have to overlap. - `Mode::PLANAR_PROJECTION` projects the images onto a plane given in the common origin frame of the inputs (bird's-eye view), driven purely by the calibration carried in the messages, so it also works without overlap. All input transformations must have the same origin camera socket.  The stitched frame carries an ImgTransformation describing the virtual camera that rendered it, so that the image can be placed in space, e.g. wrapped onto a cylinder next to a point cloud. In `Mode::PLANAR_PROJECTION` that is the pinhole view of `setView()`, relative to the common origin of the inputs. In `Mode::PANORAMA` the camera model follows `setCameraModel()`: dai::CameraModel::Perspective, Cylindrical or Equirectangular (see dai::CameraModel for their projection formulas), the focal length is the radius of the projection surface in pixels and the principal point is the pixel the panorama Z axis projects to. A panorama composed from the input calibration is expressed in the destination coordinate system of the inputs, centered at the mean of their camera centers. A visually registered panorama is only known relative to its inputs, so it is expressed through the first contributing input: in the destination coordinate system of that input's extrinsics when it carries some, and relative to that input's camera, with an AUTO socket, otherwise.
class
XFeatMonoParser
XFeatMonoParser node. Parses the output of the XFeat model from one source (e.g. one camera) into a dai::TrackedFeatures message with the keypoints of a reference frame matched to the keypoints of the current frame.  The parser consumes three output tensors, assigned from an NNArchive head by name substring or configured explicitly: the feature map (layer name containing "feats"), read in NCHW orientation as (1, descriptor size, height, width), the keypoint logits (name containing "keypoints"), read as (1, channels >= 64, height, width), and the reliability heat map (name containing "heatmaps"), read as (1, 1, height, width). Every frame is decoded into keypoints, scores and descriptors; the strongest keypoints (up to the maximum count) with a positive score are kept and their positions are scaled from the model input size to the original image size.  The parser keeps a reference frame state: calling setTrigger() stores the next decoded result as the reference after that frame's message is emitted. Frames decoded while no reference is stored produce an empty TrackedFeatures message; afterwards each frame's keypoints are matched to the reference by mutual nearest-neighbor cosine similarity and emitted as feature pairs, where match i produces the reference position with id i and age 0 followed by the matched current position with id i and age 1. A frame whose keypoint heat map has no candidate produces an empty message and leaves the reference and the pending trigger untouched.  The original image size must be configured before the pipeline starts, either through head metadata or with setOriginalSize().
class
XFeatStereoParser
XFeatStereoParser node. Parses the output of the XFeat model from two sources (e.g. two cameras - left and right) into a dai::TrackedFeatures message with the keypoints of the reference frame matched to the keypoints of the target frame.  The parser consumes three output tensors per source, assigned from an NNArchive head by name substring or configured explicitly: the feature map (layer name containing "feats"), read in NCHW orientation as (1, descriptor size, height, width), the keypoint logits (name containing "keypoints"), read as (1, channels >= 64, height, width), and the reliability heat map (name containing "heatmaps"), read as (1, 1, height, width). Both sources share one layer, size and keypoint-count configuration.  Each iteration consumes one reference message followed by one target message; the node performs no synchronization beyond these two sequential blocking reads. Both messages are decoded into keypoints, scores and descriptors; the strongest keypoints (up to the maximum count) with a positive score are kept and their positions are scaled from the model input size to the original image size. When the reference (checked first) or the target frame's keypoint heat map has no candidate, an empty TrackedFeatures message is emitted carrying that frame's timestamps and the reference frame's sequence number. Otherwise the reference keypoints are matched to the target keypoints by mutual nearest-neighbor cosine similarity and emitted as feature pairs, where match i produces the reference position with id i and age 0 followed by the matched target position with id i and age 1; the message carries the target frame's timestamps and the reference frame's sequence number, like the source parser.  The original image size must be configured before the pipeline starts, either through head metadata or with setOriginalSize().
class
YuNetParser
YuNetParser node. Parses the output of the YuNet face detection model into a dai::ImgDetections message containing the bounding boxes, labels, confidence scores and 5 facial keypoints per detected face, everything normalized to [0, 1]. The decoding is based on https://github.com/Kazuhito00/YuNet-ONNX-TFLite- Sample (Apache License 2.0).  The parser consumes three output tensors: a loc tensor with 14 values per anchor (2 bounding box center offsets, 2 bounding box size values and 5 keypoint coordinate offset pairs), a conf tensor with 2 values per anchor (non-face and face scores) and an iou tensor with 1 value per anchor. When a layer name is not configured, it is auto-detected from the incoming NNData as the single layer name starting with "loc", "conf" or "iou" respectively. The candidate scores are sqrt(conf face score * iou score clipped to [0, 1]); candidates with a score strictly greater than the confidence threshold are decoded against the YuNet anchors generated from the input size, suppressed with cv2.dnn.NMSBoxes- semantics non-maximum suppression (IoU threshold, maximum number of detections as the top-k limit) and emitted in descending score order. Keypoint coordinates are truncated to whole pixels before normalization, mirroring the source parser. The anchors are cached across messages and refreshed when the input size changes.
class

depthai.beta.node.ToFStereoFusion(depthai.DeviceNode)

method
build(self, left: depthai.node.Camera, right: depthai.node.Camera, fps: float = 30.0) -> ToFStereoFusion: ToFStereoFusion
Configures fusion from a synchronized left and right camera pair.  @note This node is supported on RVC4 devices only.  Parameter ``left``:     Left camera node.  Parameter ``right``:     Right camera node.  Parameter ``fps``:     Frame rate for the neural-depth camera inputs and ToF subnode. Must be     finite and positive. Defaults to 30 FPS.  Returns:     This node.
property
confidence
Confidence output produced by the ToF-neural fusion network, with the same optional crop and transformation as depth.
property
depth
Fused depth output, aligned to the ToF sensor. Optional cropping updates intrinsics and preserves the ToF camera pose.
property
property
inputLeft
Left camera input used when the node runs outside the RVC4 device build.
property
inputRight
Right camera input used when the node runs outside the RVC4 device build.
property
property
property
class

depthai.beta.node.ClassificationParser(depthai.DeviceNode)

method
method
getClasses(self) -> list[str]: list[str]
Returns the class names to link with the classification scores.
method
getOutputLayerName(self) -> str: str
Returns the name of the model output layer to parse.
method
getSoftmax(self) -> bool: bool
Returns whether the model output is treated as already softmaxed.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setClasses(self, classes: list[str])
Sets the class names to link with the classification scores.  The class names are expected to be in the same order as the neural network's output. The number of class names must match the number of scores produced by the model.  Parameter ``classes``:     Vector of class names
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one ClassificationParser head; use setNNArchiveHead() to select a specific head from a multi-head archive.  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be a ClassificationParser head with exactly one output layer.  Parameter ``head:``:     NNArchive head to set
method
setOutputLayerName(self, outputLayerName: str)
Sets the name of the model output layer to parse.  When left empty, the parser selects the tensor automatically if the incoming NNData contains exactly one tensor and fails otherwise.  Parameter ``outputLayerName``:     Name of the output layer
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
method
setSoftmax(self, isSoftmax: bool)
Sets whether the model output is already softmaxed.  When false, the parser applies softmax to convert the raw scores to probabilities.  Parameter ``isSoftmax``:     True when the model output is already softmaxed
property
input
Input NN results with classification data to parse.
property
out
Outputs Classifications message with classes and scores sorted in descending order of score.
class

depthai.beta.node.ClassificationSequenceParser(depthai.DeviceNode)

method
method
getClasses(self) -> list[str]: list[str]
Returns the class names to link with the per-step classification scores.
method
getConcatenateClasses(self) -> bool: bool
Returns whether the remaining classes are concatenated.
method
getIgnoredIndexes(self) -> list[int]: list[int]
Returns the class indexes ignored during classification sequence generation.
method
getOutputLayerName(self) -> str: str
Returns the name of the model output layer to parse.
method
getRemoveDuplicates(self) -> bool: bool
Returns whether consecutive duplicate classes are removed from the sequence.
method
getSoftmax(self) -> bool: bool
Returns whether the model output is treated as already softmaxed.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setClasses(self, classes: list[str])
Sets the class names to link with the per-step classification scores.  The class names are expected to be in the same order as the neural network's output. The number of class names must match the number of scores produced by the model at each sequence step.  Parameter ``classes``:     Vector of class names
method
setConcatenateClasses(self, concatenateClasses: bool)
Sets whether the remaining classes are concatenated. Used mostly for text processing.  When true and more than one class remains: when all remaining class names are at most one character long, they are joined and split on whitespace into words with a per-word mean score; otherwise all class names are joined into a single string with a " " separator and one mean score.  Parameter ``concatenateClasses``:     True to concatenate the remaining classes @note Configures startup behavior.     Send ClassificationSequenceParserConfig to inputConfig after the pipeline     starts.
method
setIgnoredIndexes(self, ignoredIndexes: list[int])
Sets the class indexes to ignore during classification sequence generation (e.g. background class, blank space).  Sequence steps whose most probable class index is listed here are dropped from the output. Every index must be within [0, nClasses - 1].  Parameter ``ignoredIndexes``:     Vector of class indexes to ignore @note Configures startup behavior. Send     ClassificationSequenceParserConfig to inputConfig after the pipeline starts.
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one ClassificationSequenceParser head; use setNNArchiveHead() to select a specific head from a multi-head archive.  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be a ClassificationSequenceParser head with exactly one output layer.  Parameter ``head:``:     NNArchive head to set
method
setOutputLayerName(self, outputLayerName: str)
Sets the name of the model output layer to parse.  When left empty, the parser selects the tensor automatically if the incoming NNData contains exactly one tensor and fails otherwise.  Parameter ``outputLayerName``:     Name of the output layer
method
setRemoveDuplicates(self, removeDuplicates: bool)
Sets whether consecutive duplicate classes are removed from the sequence.  Only consecutive duplicates are removed; repeated classes separated by other classes are kept.  Parameter ``removeDuplicates``:     True to remove consecutive duplicates from the sequence @note Configures     startup behavior. Send ClassificationSequenceParserConfig to inputConfig     after the pipeline starts.
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
method
setSoftmax(self, isSoftmax: bool)
Sets whether the model output is already softmaxed.  When false, the parser applies softmax along each sequence step to convert the raw scores to probabilities.  Parameter ``isSoftmax``:     True when the model output is already softmaxed
property
initialConfig
Configuration used until a message is received on inputConfig.
property
input
Input NN results with classification sequence data to parse.
property
inputConfig
Runtime parser configuration. When synchronized, one configuration is consumed per frame; otherwise all queued configurations are drained and the newest valid one is used.
property
out
Outputs Classifications message with classes and scores ordered by their position in the sequence.
class

depthai.beta.node.EmbeddingsParser(depthai.DeviceNode)

method
method
getOutputLayerName(self) -> str: str
Returns the name of the model output layer carrying the embeddings.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one EmbeddingsParser head; use setNNArchiveHead() to select a specific head from a multi-head archive.  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be an EmbeddingsParser head with exactly one output layer.  Parameter ``head:``:     NNArchive head to set
method
setOutputLayerName(self, outputLayerName: str)
Sets the name of the model output layer carrying the embeddings.  When left empty, the parser requires the incoming NNData to contain exactly one tensor and fails otherwise.  Parameter ``outputLayerName``:     Name of the output layer
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
property
input
Input NN results with embeddings data to validate and forward.
property
out
Outputs the unchanged NNData message containing the embeddings output layer.
class

depthai.beta.node.FastSAMParser(depthai.DeviceNode)

method
method
method
getConfidenceThreshold(self) -> float: float
Returns the confidence score threshold for detected objects.
method
getIouThreshold(self) -> float: float
Returns the non-maximum suppression overlap threshold.
method
getMaskConfidence(self) -> float: float
Returns the mask confidence threshold.
method
getMaskOutputs(self) -> list[str]: list[str]
Returns the names of the model's mask-coefficient output layers.
method
getNumClasses(self) -> int: int
Returns the number of classes in the model.
method
getPointLabel(self) -> int|None: int|None
Returns the prompt point label, or std::nullopt when it is not set.
method
getPoints(self) -> tuple[int, int]|None: tuple[int, int]|None
Returns the prompt point as (x, y), or std::nullopt when it is not set.
method
getPrompt(self) -> str: str
Returns the prompt type.
method
getProtosOutput(self) -> str: str
Returns the name of the model's prototype-masks output layer.
method
getYoloOutputs(self) -> list[str]: list[str]
Returns the names of the model's YOLO output layers.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setBoundingBox(self, bbox: typing.Annotated[list[int], pybind11_stubgen.typing_ext.FixedSize(4)])
Sets the prompt bounding box as (x1, y1, x2, y2) in model-input pixels, used by the "bbox" prompt. Unset by default; the "bbox" prompt requires it and its x2 and y2 coordinates must not be 0.  Parameter ``bbox``:     Bounding box as (x1, y1, x2, y2) @note Configures startup behavior. Send     FastSAMParserConfig to inputConfig after the pipeline starts.
method
setConfidenceThreshold(self, threshold: float)
Sets the confidence score threshold for detected objects. Detections whose score is strictly greater than the threshold are kept. Defaults to 0.5.  Parameter ``threshold``:     Confidence score threshold, must be between 0 and 1 @note Configures startup     behavior. Send FastSAMParserConfig to inputConfig after the pipeline starts.
method
setIouThreshold(self, iouThreshold: float)
Sets the non-maximum suppression overlap threshold. Boxes whose overlap with a kept box is strictly greater than the threshold are suppressed. Defaults to 0.5.  Parameter ``iouThreshold``:     Overlap threshold, must be between 0 and 1 @note Configures startup     behavior. Send FastSAMParserConfig to inputConfig after the pipeline starts.
method
setMaskConfidence(self, maskConfidence: float)
Sets the mask confidence threshold used to binarize instance masks. Mask pixels with a sigmoid probability strictly greater than the threshold belong to the instance. Defaults to 0.5.  Parameter ``maskConfidence``:     Mask confidence threshold, must be between 0 and 1 @note Configures startup     behavior. Send FastSAMParserConfig to inputConfig after the pipeline starts.
method
setMaskOutputs(self, maskOutputs: list[str])
Sets the names of the model's mask-coefficient output layers. Only names containing "mask" are used, sorted by name and index-aligned with the sorted YOLO output layers; when empty, all layer names of the incoming NNData containing "mask" are used. Defaults to ["output1_masks", "output2_masks", "output3_masks"].  Parameter ``maskOutputs``:     Names of the mask output layers
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one FastSAMParser head; use setNNArchiveHead() to select a specific head from a multi-head archive.  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head's output layer names containing "_yolo" configure the YOLO output layers and those containing "_masks" the mask output layers (each only when at least one matches). The confidence threshold, number of classes, NMS threshold, mask confidence, prompt, points, point label and bounding box are read from the head metadata when present.  Parameter ``head:``:     NNArchive head to set
method
setNumClasses(self, numClasses: int)
Sets the number of classes in the model. The YOLO output tensors must have numClasses + 5 channels. Defaults to 1.  Parameter ``numClasses``:     Number of classes, must be greater than 0
method
setPointLabel(self, pointLabel: int)
Sets the prompt point label, used by the "point" prompt: 1 adds the instance masks containing the point, 0 subtracts them. Unset by default; the "point" prompt requires it.  Parameter ``pointLabel``:     Point label @note Configures startup behavior. Send FastSAMParserConfig to     inputConfig after the pipeline starts.
method
setPoints(self, x: int, y: int)
Sets the prompt point as (x, y) in model-input pixels, used by the "point" prompt. Unset by default; the "point" prompt requires it.  Parameter ``x``:     Point x coordinate  Parameter ``y``:     Point y coordinate @note Configures startup behavior. Send     FastSAMParserConfig to inputConfig after the pipeline starts.
method
setPrompt(self, prompt: str)
Sets the prompt type: "everything" emits every detected instance, "bbox" the single instance mask with the highest IoU against the prompt bounding box (see setBoundingBox()), and "point" the combination of the instance masks containing the prompt point (see setPoints() and setPointLabel()). Defaults to "everything".  Parameter ``prompt``:     Prompt type, one of "everything", "bbox" or "point" @note Configures startup     behavior. Send FastSAMParserConfig to inputConfig after the pipeline starts.
method
setProtosOutput(self, protosOutput: str)
Sets the name of the model's prototype-masks output layer; when empty, "protos_output" is used. Defaults to "protos_output".  Parameter ``protosOutput``:     Name of the protos output layer
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
method
setYoloOutputs(self, yoloOutputs: list[str])
Sets the names of the model's YOLO output layers. The layers are processed sorted by name, so the stride-8 head must come first in sort order. Defaults to ["output1_yolov8", "output2_yolov8", "output3_yolov8"].  Parameter ``yoloOutputs``:     Names of the YOLO output layers
property
initialConfig
Configuration used until a message is received on inputConfig.
property
input
Input NN results with FastSAM data to parse.
property
inputConfig
Runtime parser configuration. When synchronized, one configuration is consumed per frame; otherwise all queued configurations are drained and the newest valid one is used.
property
out
Outputs SegmentationMask message with the resulting segmentation masks given the prompt.
class

depthai.beta.node.HRNetParser(depthai.DeviceNode)

method
method
method
getLabelNames(self) -> list[str]: list[str]
Returns the label names for the keypoints.
method
getOutputLayerName(self) -> str: str
Returns the name of the model output layer to parse.
method
getScoreThreshold(self) -> float: float
Returns the confidence score threshold for detected keypoints.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setEdges(self, edges: list[typing.Annotated[list[int], pybind11_stubgen.typing_ext.FixedSize(2)]])
Sets the skeleton edges as pairs of keypoint indices used for visualizing the skeleton.  Example: {{0, 1}, {1, 2}, {2, 3}, {3, 0}} connects keypoint 0 to keypoint 1, keypoint 1 to keypoint 2, etc.  Parameter ``edges``:     Vector of keypoint index pairs
method
setLabelNames(self, labelNames: list[str])
Sets the label names for the keypoints, indexed by keypoint index.  Parameter ``labelNames``:     Vector of label names
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one HRNetParser head; use setNNArchiveHead() to select a specific head from a multi-head archive.  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be an HRNetParser head with exactly one output layer.  Parameter ``head:``:     NNArchive head to set
method
setOutputLayerName(self, outputLayerName: str)
Sets the name of the model output layer to parse.  When left empty, the parser selects the tensor automatically if the incoming NNData contains exactly one tensor and fails otherwise.  Parameter ``outputLayerName``:     Name of the output layer
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
method
setScoreThreshold(self, threshold: float)
Sets the confidence score threshold for detected keypoints. Keypoints with a score strictly below the threshold are dropped.  Parameter ``threshold``:     Confidence score threshold, must be between 0 and 1 @note Configures startup     behavior. Send HRNetParserConfig to inputConfig after the pipeline starts.
property
initialConfig
Configuration used until a message is received on inputConfig.
property
input
Input NN results with heatmaps data to parse.
property
inputConfig
Runtime parser configuration. When synchronized, one configuration is consumed per frame; otherwise all queued configurations are drained and the newest valid one is used.
property
out
Outputs Keypoints message with the detected body keypoints.
class

depthai.beta.node.ImageOutputParser(depthai.DeviceNode)

method
method
getBGROutput(self) -> bool: bool
Returns the flag indicating whether the model output image is in BGR (Blue- Green-Red) channel order.
method
getOutputLayerName(self) -> str: str
Returns the name of the model output layer to parse.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setBGROutput(self, outputIsBGR: bool = True)
Sets the flag indicating whether the model output image is in BGR (Blue-Green- Red) channel order.  When false (the default), a color model output is treated as RGB and its channels are swapped to BGR before being emitted.  Parameter ``outputIsBGR``:     True when the model output image is already BGR, defaults to true
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one ImageOutputParser head; use setNNArchiveHead() to select a specific head from a multi-head archive.  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be an ImageOutputParser head with exactly one output layer.  Parameter ``head:``:     NNArchive head to set
method
setOutputLayerName(self, outputLayerName: str)
Sets the name of the model output layer to parse.  When left empty, the parser selects the tensor automatically if the incoming NNData contains exactly one tensor and fails otherwise.  Parameter ``outputLayerName``:     Name of the output layer
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
property
input
Input NN results with image tensor data to parse.
property
out
Outputs ImgFrame message with the model output image, e.g. a denoised or enhanced image.
class

depthai.beta.node.ImgDetectionsFilter(depthai.DeviceNode)

method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
property
initialConfig
Configuration used until a message is received on inputConfig.  The default configuration forwards detections unchanged.
property
input
Image detections to filter.
property
inputConfig
Runtime filter configuration. The most recently received configuration is reused for subsequent detection messages.
property
output
Filtered image detections.
class

depthai.beta.node.KeypointParser(depthai.DeviceNode)

method
method
method
getLabelNames(self) -> list[str]: list[str]
Returns the label names for the keypoints.
method
getNumKeypoints(self) -> int|None: int|None
Returns the number of keypoints the model detects, or std::nullopt when not configured.
method
getOutputLayerName(self) -> str: str
Returns the name of the model output layer to parse.
method
getScaleFactor(self) -> float: float
Returns the scale factor to divide the keypoint coordinates by.
method
getScoreThreshold(self) -> float|None: float|None
Returns the confidence score threshold for detected keypoints, or std::nullopt when not configured.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setEdges(self, edges: list[typing.Annotated[list[int], pybind11_stubgen.typing_ext.FixedSize(2)]])
Sets the skeleton edges as pairs of keypoint indices used for visualizing the skeleton.  Example: {{0, 1}, {1, 2}, {2, 3}, {3, 0}} connects keypoint 0 to keypoint 1, keypoint 1 to keypoint 2, etc.  Parameter ``edges``:     Vector of keypoint index pairs
method
setLabelNames(self, labelNames: list[str])
Sets the label names for the keypoints, indexed by keypoint index.  Parameter ``labelNames``:     Vector of label names
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one KeypointParser head; use setNNArchiveHead() to select a specific head from a multi-head archive.  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be a KeypointParser head with exactly one output layer.  Parameter ``head:``:     NNArchive head to set
method
setNumKeypoints(self, nKeypoints: int)
Sets the number of keypoints the model detects.  Must be configured before the pipeline starts, either explicitly or through an NNArchive head.  Parameter ``nKeypoints``:     Number of keypoints, must be greater than 0
method
setOutputLayerName(self, outputLayerName: str)
Sets the name of the model output layer to parse.  When left empty, the parser selects the tensor automatically if the incoming NNData contains exactly one tensor and fails otherwise.  Parameter ``outputLayerName``:     Name of the output layer
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
method
setScaleFactor(self, scaleFactor: float)
Sets the scale factor to divide the keypoint coordinates by.  Parameter ``scaleFactor``:     Scale factor, must be greater than 0
method
setScoreThreshold(self, threshold: float)
Sets the confidence score threshold for detected keypoints.  Parameter ``threshold``:     Confidence score threshold, must be between 0 and 1
property
input
Input NN results with keypoints data to parse.
property
out
Outputs Keypoints message with the parsed 2D or 3D keypoints.
class

depthai.beta.node.LaneDetectionParser(depthai.DeviceNode)

method
method
getClsNumPerLane(self) -> int|None: int|None
Returns the number of points per lane, or std::nullopt when not configured.
method
getGridingNum(self) -> int|None: int|None
Returns the griding number, or std::nullopt when not configured.
method
getInputSize(self) -> tuple[int, int]|None: tuple[int, int]|None
Returns the model input image size as (width, height), or std::nullopt when not configured.
method
getOutputLayerName(self) -> str: str
Returns the name of the model output layer to parse.
method
getRowAnchors(self) -> list[int]: list[int]
Returns the row anchors, or an empty vector when not configured.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setClsNumPerLane(self, clsNumPerLane: int)
Sets the number of points per lane.  Must be configured before the pipeline starts, either explicitly or through an NNArchive head.  Parameter ``clsNumPerLane``:     Number of points per lane, must be greater than 0
method
setGridingNum(self, gridingNum: int)
Sets the griding number, the number of column samples the model predicts lane positions over.  Must be configured before the pipeline starts, either explicitly or through an NNArchive head.  Parameter ``gridingNum``:     Griding number, must be greater than 1
method
setInputSize(self, width: int, height: int)
Sets the model input image size the emitted points are computed against and normalized by.  Must be configured before the pipeline starts. Configuring from a full NNArchive derives it from the model input's declared shape and layout; the most recent configuration wins.  Parameter ``width``:     Input image width, must be greater than 0  Parameter ``height``:     Input image height, must be greater than 0
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one LaneDetectionParser head and exactly one model input; use setNNArchiveHead() to select a specific head from a multi-head archive. The input size is derived from the model input's declared shape and layout (NHWC or NCHW).  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be a LaneDetectionParser head with exactly one output layer.  Parameter ``head:``:     NNArchive head to set @note A head carries no model input metadata, so the     input size must additionally be configured with setInputSize().
method
setOutputLayerName(self, outputLayerName: str)
Sets the name of the model output layer to parse.  When left empty, the parser selects the tensor automatically if the incoming NNData contains exactly one tensor and fails otherwise.  Parameter ``outputLayerName``:     Name of the output layer
method
setRowAnchors(self, rowAnchors: list[int])
Sets the row anchors, the image rows at which the model predicts lane positions.  Must be configured before the pipeline starts, either explicitly or through an NNArchive head, and must contain at least as many entries as the number of points per lane.  Parameter ``rowAnchors``:     Row anchors, must not be empty
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
property
input
Input NN results with lane detection data to parse.
property
out
Outputs Clusters message with the detected lanes represented as clusters of points.
class

depthai.beta.node.MapOutputParser(depthai.DeviceNode)

method
method
getMinMaxScaling(self) -> bool: bool
Returns the flag indicating whether the map is scaled to the [0, 1] range.
method
getOutputLayerName(self) -> str: str
Returns the name of the model output layer to parse.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setMinMaxScaling(self, minMaxScaling: bool = True)
Sets the flag indicating whether the map is scaled to the [0, 1] range.  When true, the map values are min-max scaled to [0, 1]; a constant map is left unchanged. Defaults to false.  Parameter ``minMaxScaling``:     True to scale the map to the [0, 1] range, defaults to true @note Configures     startup behavior. Send MapOutputParserConfig to inputConfig after the     pipeline starts.
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one MapOutputParser head; use setNNArchiveHead() to select a specific head from a multi-head archive.  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be a MapOutputParser head with exactly one output layer.  Parameter ``head:``:     NNArchive head to set
method
setOutputLayerName(self, outputLayerName: str)
Sets the name of the model output layer to parse.  When left empty, the parser selects the tensor automatically if the incoming NNData contains exactly one tensor and fails otherwise.  Parameter ``outputLayerName``:     Name of the output layer
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
property
initialConfig
Configuration used until a message is received on inputConfig.
property
input
Input NN results with map tensor data to parse.
property
inputConfig
Runtime parser configuration. When synchronized, one configuration is consumed per frame; otherwise all queued configurations are drained and the newest valid one is used.
property
out
Outputs Map2D message with the parsed 2D map, e.g. a depth or density map.
class

depthai.beta.node.MLSDParser(depthai.DeviceNode)

method
method
getDistanceThreshold(self) -> float: float
Returns the distance threshold for detected lines.
method
getInputSize(self) -> tuple[int, int]: tuple[int, int]
Returns the model input image size as (width, height).
method
getOutputLayerHeat(self) -> str: str
Returns the name of the output layer containing the heat tensor, or an empty string when not configured.
method
getOutputLayerTPMap(self) -> str: str
Returns the name of the output layer containing the tpMap tensor, or an empty string when not configured.
method
getScoreThreshold(self) -> float: float
Returns the confidence score threshold for detected lines.
method
getTopK(self) -> int: int
Returns the number of top candidates to keep.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setDistanceThreshold(self, distanceThreshold: float)
Sets the distance threshold for detected lines. Candidates whose length in heat map grid units is strictly above the threshold are kept.  Parameter ``distanceThreshold``:     Distance threshold @note Configures startup behavior. Send MLSDParserConfig     to inputConfig after the pipeline starts.
method
setInputSize(self, width: int, height: int)
Sets the model input image size the emitted line coordinates are normalized by, x coordinates by the width and y coordinates by the height.  Defaults to 512x512, the input size of all known M-LSD models. Configuring from a full NNArchive derives it from the model input's declared shape and layout; the most recent configuration wins.  Parameter ``width``:     Input image width, must be greater than 0  Parameter ``height``:     Input image height, must be greater than 0
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one MLSDParser head and exactly one model input; use setNNArchiveHead() to select a specific head from a multi-head archive. The input size is derived from the model input's declared shape and layout (NHWC or NCHW).  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be an MLSDParser head with exactly two output layers; the layer whose name contains "tpMap" is used as the tpMap layer and the layer whose name contains "heat" as the heat layer.  Parameter ``head:``:     NNArchive head to set @note A head carries no model input metadata, so the     input size keeps its current value (512x512 by default); use setInputSize()     for models with a different input size.
method
setOutputLayerHeat(self, outputLayerHeat: str)
Sets the name of the output layer containing the heat tensor.  Must be configured before the pipeline starts, either explicitly or through an NNArchive head.  Parameter ``outputLayerHeat``:     Name of the output layer containing the heat tensor
method
setOutputLayerTPMap(self, outputLayerTPMap: str)
Sets the name of the output layer containing the tpMap tensor.  Must be configured before the pipeline starts, either explicitly or through an NNArchive head.  Parameter ``outputLayerTPMap``:     Name of the output layer containing the tpMap tensor
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
method
setScoreThreshold(self, scoreThreshold: float)
Sets the confidence score threshold for detected lines. Candidates with a heat score strictly above the threshold are kept.  Parameter ``scoreThreshold``:     Confidence score threshold @note Configures startup behavior. Send     MLSDParserConfig to inputConfig after the pipeline starts.
method
setTopK(self, topK: int)
Sets the number of top candidates to keep.  The number of candidates is capped at the heat map size when decoding.  Parameter ``topK``:     Number of top candidates to keep, must be positive @note Configures startup     behavior. Send MLSDParserConfig to inputConfig after the pipeline starts.
property
initialConfig
Configuration used until a message is received on inputConfig.
property
input
Input NN results with line detection data to parse.
property
inputConfig
Runtime parser configuration. When synchronized, one configuration is consumed per frame; otherwise all queued configurations are drained and the newest valid one is used.
property
out
Outputs Lines message with the detected lines and confidence scores.
class

depthai.beta.node.MPPalmDetectionParser(depthai.DeviceNode)

method
method
getConfidenceThreshold(self) -> float: float
Returns the confidence score threshold for detected hands.
method
getIouThreshold(self) -> float: float
Returns the non-maximum suppression (IoU) threshold.
method
getLabelNames(self) -> list[str]: list[str]
Returns the label names for the detected hands.
method
getMaxDetections(self) -> int: int
Returns the maximum number of detections to keep.
method
getOutputLayerNames(self) -> list[str]: list[str]
Returns the names of the model output layers relevant to the parser.
method
getScale(self) -> int: int
Returns the scale of the model input image in pixels.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setConfidenceThreshold(self, threshold: float)
Sets the confidence score threshold for detected hands. Detections with a sigmoid score strictly above the threshold are kept.  Parameter ``threshold``:     Confidence score threshold @note Configures startup behavior. Send     MPPalmDetectionParserConfig to inputConfig after the pipeline starts.
method
setIouThreshold(self, threshold: float)
Sets the non-maximum suppression (IoU) threshold.  Parameter ``threshold``:     Non-maximum suppression threshold @note Configures startup behavior. Send     MPPalmDetectionParserConfig to inputConfig after the pipeline starts.
method
setLabelNames(self, labelNames: list[str])
Sets the label names for the detected hands. The first label name is assigned to every detection (all detections carry label 0). When empty, no label name is assigned.  Parameter ``labelNames``:     List of label names
method
setMaxDetections(self, maxDetections: int)
Sets the maximum number of detections to keep.  Parameter ``maxDetections``:     Maximum number of detections to keep @note Configures startup behavior. Send     MPPalmDetectionParserConfig to inputConfig after the pipeline starts.
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one MPPalmDetectionParser head; use setNNArchiveHead() to select a specific head from a multi-head archive.  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be an MPPalmDetectionParser head with exactly two output layers.  Parameter ``head:``:     NNArchive head to set
method
setOutputLayerNames(self, outputLayerNames: list[str])
Sets the names of the model output layers relevant to the parser. Exactly two layer names are required.  Parameter ``outputLayerNames``:     Names of the output layers
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
method
setScale(self, scale: int)
Sets the scale of the model input image in pixels (e.g. 192 for a 192x192 model). The SSD anchors used for decoding are generated from the scale; a scale that does not match the model input size fails decoding with an anchor count mismatch.  Parameter ``scale``:     Scale of the input image
property
initialConfig
Configuration used when the parser starts.
property
input
Input NN results with palm detection data to parse.
property
inputConfig
Runtime parser configuration. In synchronized mode one configuration is consumed per input frame; otherwise all queued configurations are drained and the newest valid one is retained.
property
out
Outputs ImgDetections message with the rotated bounding boxes, labels and confidence scores of the detected hands.
class

depthai.beta.node.PPTextDetectionParser(depthai.DeviceNode)

method
method
getConfidenceThreshold(self) -> float: float
Returns the confidence score threshold for the detected text bounding boxes.
method
getMaskThreshold(self) -> float: float
Returns the mask threshold for creating the binary text mask from the model output probabilities.
method
getMaxDetections(self) -> int: int
Returns the maximum number of candidate bounding boxes.
method
getOutputLayerName(self) -> str: str
Returns the name of the model output layer holding the text probability map.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setConfidenceThreshold(self, threshold: float)
Sets the confidence score threshold for the detected text bounding boxes. Candidates with a score strictly below the threshold are dropped.  Parameter ``threshold``:     Confidence score threshold @note Configures startup behavior. Send     PPTextDetectionParserConfig to inputConfig after the pipeline starts.
method
setMaskThreshold(self, maskThreshold: float)
Sets the mask threshold for creating the binary text mask from the model output probabilities. Probabilities strictly above the threshold belong to the mask.  Parameter ``maskThreshold``:     Mask threshold @note Configures startup behavior. Send     PPTextDetectionParserConfig to inputConfig after the pipeline starts.
method
setMaxDetections(self, maxDetections: int)
Sets the maximum number of candidate bounding boxes. When more candidate contours are found, only the largest by area are kept.  Parameter ``maxDetections``:     Maximum number of candidate bounding boxes @note Configures startup     behavior. Send PPTextDetectionParserConfig to inputConfig after the pipeline     starts.
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one PPTextDetectionParser head; use setNNArchiveHead() to select a specific head from a multi-head archive.  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head configures the confidence threshold, the mask threshold and the maximum number of detections when present in its metadata. The head's declared output names are not consumed: the parser resolves the single runtime output tensor by itself (or uses the explicitly configured output layer name), mirroring the source parser; archives whose head output name differs from the model's declared output name therefore parse correctly.  Parameter ``head:``:     NNArchive head to set
method
setOutputLayerName(self, outputLayerName: str)
Sets the name of the model output layer holding the text probability map. When empty (the default), the layer is resolved automatically from single-tensor NN results; multi-tensor results require an explicit name.  Parameter ``outputLayerName``:     Name of the output layer
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
property
initialConfig
Configuration used when the parser starts.
property
input
Input NN results with text detection probability map to parse.
property
inputConfig
Runtime parser configuration. In synchronized mode one configuration is consumed per input frame; otherwise all queued configurations are drained and the newest valid one is retained.
property
out
Outputs ImgDetections message with the rotated bounding boxes and confidence scores of the detected text.
class

depthai.beta.node.RegressionParser(depthai.DeviceNode)

method
method
getOutputLayerName(self) -> str: str
Returns the name of the model output layer to parse.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one RegressionParser head; use setNNArchiveHead() to select a specific head from a multi-head archive.  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be a RegressionParser head with exactly one output layer.  Parameter ``head:``:     NNArchive head to set
method
setOutputLayerName(self, outputLayerName: str)
Sets the name of the model output layer to parse.  When left empty, the parser selects the tensor automatically if the incoming NNData contains exactly one tensor and fails otherwise.  Parameter ``outputLayerName``:     Name of the output layer
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
property
input
Input NN results with regression data to parse.
property
out
Outputs Predictions message with the predicted value(s).
class

depthai.beta.node.RFDETRParser(depthai.DeviceNode)

method
method
getConfidenceThreshold(self) -> float: float
Returns the confidence score threshold for detected objects.
method
getInputSize(self) -> tuple[int, int]|None: tuple[int, int]|None
Returns the model input image size as (width, height), or std::nullopt when it is not set.
method
getLabelNames(self) -> list[str]: list[str]
Returns the label names for the detected objects.
method
getMaskConfidence(self) -> float: float
Returns the mask confidence threshold.
method
getMaxDetections(self) -> int: int
Returns the maximum number of detections to keep.
method
getOutputLayerNames(self) -> list[str]: list[str]
Returns the names of the model output layers.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setConfidenceThreshold(self, threshold: float)
Sets the confidence score threshold for detected objects. Detections with a score strictly greater than the threshold are kept. Defaults to 0.5.  Parameter ``threshold``:     Confidence score threshold, must be between 0 and 1 @note Configures startup     behavior. Send RFDETRParserConfig to inputConfig after the pipeline starts.
method
setInputSize(self, width: int, height: int)
Sets the model input image size the segmentation mask is emitted at. Unset by default; segmentation mode requires it to be configured from an NNArchive or with this setter before the parser processes messages. Detection mode does not use it.  Configuring from a full NNArchive derives it from the first model input's declared shape and layout; the most recent configuration wins.  Parameter ``width``:     Input image width, must be greater than 0  Parameter ``height``:     Input image height, must be greater than 0
method
setLabelNames(self, labelNames: list[str])
Sets the label names for the detected objects, indexed by the class label. A detection whose label is out of range receives the name "class_<label>". When empty, no label names are assigned. Defaults to empty.  Parameter ``labelNames``:     List of label names
method
setMaskConfidence(self, maskConfidence: float)
Sets the mask confidence threshold used to binarize instance segmentation masks in segmentation mode. Mask pixels with a sigmoid probability strictly greater than the threshold belong to the instance. Defaults to 0.5.  Parameter ``maskConfidence``:     Mask confidence threshold, must be between 0 and 1 @note Configures startup     behavior. Send RFDETRParserConfig to inputConfig after the pipeline starts.
method
setMaxDetections(self, maxDetections: int)
Sets the maximum number of detections to keep, applied to the detections ordered by descending score. In segmentation mode the applied limit is additionally capped at 255, the maximum number of instances the segmentation mask can encode. Defaults to 300.  Parameter ``maxDetections``:     Maximum number of detections to keep, must be greater than 0 @note     Configures startup behavior. Send RFDETRParserConfig to inputConfig after     the pipeline starts.
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one RFDETRParser head; use setNNArchiveHead() to select a specific head from a multi-head archive. The input size is derived from the first model input's declared shape and layout (NHWC or NCHW).  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be an RFDETRParser head with 2 output layers (boxes, class logits) for detection or 3 (boxes, class logits, mask logits) for segmentation.  Parameter ``head:``:     NNArchive head to set @note A head carries no model input metadata, so the     input size keeps its current value; segmentation mode requires it to be     configured with setInputSize() when it is not set yet.
method
setOutputLayerNames(self, outputLayerNames: list[str])
Sets the names of the model output layers, positionally: the boxes layer, the class logits layer and, in segmentation mode, the mask logits layer. Must hold 2 or 3 names.  When left empty, all layer names of the incoming NNData are used in their reported order.  Parameter ``outputLayerNames``:     Names of the output layers
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
property
initialConfig
Configuration used when the parser starts.
property
input
Input NN results with RF-DETR detection data to parse.
property
inputConfig
Runtime parser configuration. In synchronized mode one configuration is consumed per input frame; otherwise all queued configurations are drained and the newest valid one is retained.
property
out
Outputs ImgDetections message with the bounding boxes, labels and confidence scores of the detected objects and, in segmentation mode, the instance segmentation mask.
class

depthai.beta.node.SCRFDParser(depthai.DeviceNode)

method
method
getConfidenceThreshold(self) -> float: float
Returns the confidence score threshold for detected objects.
method
getFeatStrideFPN(self) -> list[int]: list[int]
Returns the feature strides of the FPN.
method
getInputSize(self) -> tuple[int, int]: tuple[int, int]
Returns the model input image size as (width, height).
method
getIouThreshold(self) -> float: float
Returns the non-maximum suppression (IoU) threshold.
method
getLabelNames(self) -> list[str]: list[str]
Returns the label names for the detected objects.
method
getMaxDetections(self) -> int: int
Returns the maximum number of detections to keep.
method
getNumAnchors(self) -> int: int
Returns the number of anchors per feature map position.
method
getOutputLayerNames(self) -> list[str]: list[str]
Returns the names of the model output layers relevant to the parser.
method
runOnHost(self) -> bool: bool
Returns true when this node runs on the host.  Host-only pipelines always run the node on the host.
method
setConfidenceThreshold(self, threshold: float)
Sets the confidence score threshold for detected objects. Detections with a score greater than or equal to the threshold (inclusive) are kept.  Parameter ``threshold``:     Confidence score threshold @note Configures startup behavior. Send     SCRFDParserConfig to inputConfig after the pipeline starts.
method
setFeatStrideFPN(self, featStrideFpn: list[int])
Sets the feature strides of the FPN. One score_{stride}, bbox_{stride} and kps_{stride} layer triple is parsed per stride. Defaults to (8, 16, 32).  Parameter ``featStrideFpn``:     Feature strides, every stride must be greater than 0
method
setInputSize(self, width: int, height: int)
Sets the model input image size the anchor centers are computed against and the emitted coordinates are normalized by. Defaults to (640, 640).  Configuring from a full NNArchive derives it from the model input's declared shape and layout; the most recent configuration wins.  Parameter ``width``:     Input image width, must be greater than 0  Parameter ``height``:     Input image height, must be greater than 0
method
setIouThreshold(self, threshold: float)
Sets the non-maximum suppression (IoU) threshold. Candidates whose overlap with a kept detection is at most the threshold (inclusive) survive suppression.  Parameter ``threshold``:     Non-maximum suppression threshold @note Configures startup behavior. Send     SCRFDParserConfig to inputConfig after the pipeline starts.
method
setLabelNames(self, labelNames: list[str])
Sets the label names for the detected objects. The first label name is assigned to every detection (all detections carry label 0). When empty, no label name is assigned. Defaults to ("Face").  Parameter ``labelNames``:     List of label names
method
setMaxDetections(self, maxDetections: int)
Sets the maximum number of detections to keep.  Parameter ``maxDetections``:     Maximum number of detections to keep @note Configures startup behavior. Send     SCRFDParserConfig to inputConfig after the pipeline starts.
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one SCRFDParser head and exactly one model input; use setNNArchiveHead() to select a specific head from a multi-head archive. The input size is derived from the model input's declared shape and layout (NHWC or NCHW).  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be an SCRFDParser head with an equal number of score, bbox and kps output layers.  Parameter ``head:``:     NNArchive head to set @note A head carries no model input metadata, so the     input size keeps its current value; configure it with setInputSize() when it     differs from the default.
method
setNumAnchors(self, numAnchors: int)
Sets the number of anchors per feature map position. Defaults to 2.  Parameter ``numAnchors``:     Number of anchors; values of 1 or less yield one anchor per position,     mirroring the source behavior
method
setOutputLayerNames(self, outputLayerNames: list[str])
Sets the names of the model output layers relevant to the parser. The parser looks up the per-stride score_{stride}, bbox_{stride} and kps_{stride} layer names in this list.  When left empty, the list is resolved from the layer names of the first incoming NNData.  Parameter ``outputLayerNames``:     Names of the output layers
method
setRunOnHost(self, runOnHost: bool)
Select whether the node runs on the host or device.
property
initialConfig
Configuration used when the parser starts.
property
input
Input NN results with SCRFD detection data to parse.
property
inputConfig
Runtime parser configuration. In synchronized mode one configuration is consumed per input frame; otherwise all queued configurations are drained and the newest valid one is retained.
property
out
Outputs ImgDetections message with the bounding boxes, labels, confidence scores and keypoints of the detected objects.
class

depthai.beta.node.SuperAnimalParser(depthai.DeviceNode)

method
method
method
getLabelNames(self) -> list[str]: list[str]
Returns the label names for the keypoints.
method
getNumKeypoints(self) -> int: int
Returns the number of keypoints the model detects.
method
getOutputLayerName(self) -> str: str
Returns the name of the model output layer to parse.
method
getScaleFactor(self) -> float: float
Returns the scale factor the keypoint coordinates are scaled and normalized by.
method
getScoreThreshold(self) -> float: float
Returns the confidence score threshold for detected keypoints.
method
runOnHost(self) -> bool: bool
Check if the node is set to run on host.
method
setEdges(self, edges: list[typing.Annotated[list[int], pybind11_stubgen.typing_ext.FixedSize(2)]])
Sets the skeleton edges as pairs of keypoint indices used for visualizing the skeleton.  Example: {{0, 1}, {1, 2}, {2, 3}, {3, 0}} connects keypoint 0 to keypoint 1, keypoint 1 to keypoint 2, etc.  Parameter ``edges``:     Vector of keypoint index pairs
method
setLabelNames(self, labelNames: list[str])
Sets the label names for the keypoints, indexed by keypoint index.  Parameter ``labelNames``:     Vector of label names
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one SuperAnimalParser head; use setNNArchiveHead() to select a specific head from a multi-head archive.  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be a SuperAnimalParser head with exactly one output layer.  Parameter ``head:``:     NNArchive head to set
method
setNumKeypoints(self, nKeypoints: int)
Sets the number of keypoints the model detects.  Informational only: the decoding derives the number of keypoints from the heatmap tensor's last dimension.  Parameter ``nKeypoints``:     Number of keypoints, must be greater than 0
method
setOutputLayerName(self, outputLayerName: str)
Sets the name of the model output layer to parse.  When left empty, the parser selects the tensor automatically if the incoming NNData contains exactly one tensor and fails otherwise.  Parameter ``outputLayerName``:     Name of the output layer
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device. By default, the node runs on the device.
method
setScaleFactor(self, scaleFactor: float)
Sets the scale factor the keypoint coordinates are scaled and normalized by, typically the model input size.  Parameter ``scaleFactor``:     Scale factor, must be greater than 0
method
setScoreThreshold(self, threshold: float)
Sets the confidence score threshold for detected keypoints. Keypoints with a score strictly below the threshold are dropped.  Parameter ``threshold``:     Confidence score threshold, must be between 0 and 1 @note Configures startup     behavior. Send SuperAnimalParserConfig to inputConfig after the pipeline     starts.
property
initialConfig
Configuration used until a message is received on inputConfig.
property
input
Input NN results with heatmaps data to parse.
property
inputConfig
Runtime parser configuration. When synchronized, one configuration is consumed per frame; otherwise all queued configurations are drained and the newest valid one is used.
property
out
Outputs Keypoints message with the detected animal keypoints.
class

depthai.beta.node.Stitching(depthai.DeviceNode)

class
Mode
Stitching mode.  Members:    PANORAMA    PLANAR_PROJECTION
class
SeamFinder
Seam estimation method.  Members:    NONE    VORONOI    DP_COLOR    DP_COLOR_GRAD    GRAPHCUT_COLOR    GRAPHCUT_COLOR_GRAD
class
Plane
A plane used by planar projection stitching.
class
VirtualCamera
The pinhole camera used to render a planar projection.
method
method
method
method
method
method
method
method
getNumInputs(self) -> int: int
Number of inputs the node was built with.
method
method
method
method
getUseInputCalibration(self) -> bool: bool
Return whether panorama composition uses the calibration carried by the input ImgTransformations.
method
method
resetTransform(self)
Discard the fixed transform and composition state and re-run the estimation. In `Mode::PLANAR_PROJECTION` the projection maps, seams and exposure gains are rebuilt from the next synced group. In non-continuous `Mode::PANORAMA`, registration is repeated and the fixed maps, regions, seams and exposure parameters are rebuilt.
method
runOnHost(self) -> bool: bool
Check whether the node is configured to run on host.
method
setCameraModel(self, model: depthai.CameraModel)
Set the projection surface the images are warped onto. Defaults to Equirectangular (a sphere), same as OpenCV. Only used in `Mode::PANORAMA`.  Parameter ``model``:     dai::CameraModel::Equirectangular, Cylindrical or Perspective  Throws:     std::invalid_argument for any other model
method
setContinuous(self, continuous: bool)
Re-estimate the camera parameters on every frame. Only used in `Mode::PANORAMA`.  When true, registration runs for every synced group, which is slow but tolerates cameras that move relative to each other. When false, registration evaluates getEstimationFrames() complete candidates without composing them, selects the one with the strongest geometrically consistent feature-match score, and then starts emitting panoramas using that transform. Projection maps, output regions, seam masks and exposure parameters are prepared with the first emitted panorama and reused for subsequent groups.
method
setEstimationFrames(self, frames: int)
Number of complete registration candidates evaluated before the strongest transform is fixed. Failed registrations, oversized candidates, and candidates that omit an input do not count. No panorama is emitted while the candidates are being evaluated. Only used when continuous is false.
method
setMaxPanoramaSize(self, width: int, height: int)
Reject panorama registrations whose projected canvas exceeds this size before OpenCV allocates and composes it. This protects against degenerate feature matches producing extremely large canvases. By default the size is unbounded.
method
setMaxRange(self, range: float, unit: depthai.LengthUnit = ...)
Distance from a camera center beyond which the plane is not painted anymore. Bounds the automatic view and cuts off the region around the horizon, where a few pixels are stretched over a large part of the plane. Defaults to 10 meters.
method
setMaxViewSize(self, width: int, height: int)
Upper bound on the size of the automatically computed view, in pixels. Defaults to 1920x1920.
method
setMinIncidenceAngle(self, degrees: float)
Smallest angle between a camera ray and the plane for the ray to still be used. Rays hitting the plane at a shallower angle are heavily stretched, so they are dropped. Defaults to 5 degrees.
method
setMode(self, mode: Stitching.Mode)
Set the stitching mode. `Mode::PLANAR_PROJECTION` additionally needs a plane, see `setPlane()`.
method
setPanoConfidenceThreshold(self, threshold: float)
Confidence below which an image is dropped from the panorama
method
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or an RVC4 device. By default, the node runs on host.
method
setSeamFinder(self, finder: Stitching.SeamFinder)
Set the panorama seam finder. In calibrated panorama mode, `NONE` selects direct composition; other values also enable exposure compensation and multiband blending.
method
setSyncThreshold(self, syncThreshold: datetime.timedelta)
Set the maximal interval between messages of a synced group.  Parameter ``syncThreshold``:     Maximal interval between messages in the group
method
setUseInputCalibration(self, useInputCalibration: bool)
Use the intrinsics and rotations carried by the input ImgTransformations to compose a panorama.  All inputs must be expressed relative to exactly the same destination device ID and camera socket. Translation is ignored, so all camera centers are treated as coincident. Cylindrical panoramas use the normalized mean input camera Y axis as the cylinder axis. When enabled, panorama composition starts from the first synchronized group without feature matching or bundle adjustment. With `SeamFinder::NONE`, warped inputs are copied in order and later inputs replace earlier ones in overlapping regions. Other seam finders enable seam estimation, exposure compensation, and multiband blending. The prepared composition is reused for subsequent groups. Only undistorted inputs are accepted. Only used in `Mode::PANORAMA`.
method
setView(self, view: Stitching.VirtualCamera)
Camera the plane is rendered from, in `Mode::PLANAR_PROJECTION`.  By default the view is computed from the content: the node intersects the field of view of every input with the plane and places a camera looking straight at the plane so that all of the footprints fit, at a resolution derived from the inputs and bounded by `setMaxViewSize()`.
method
property
inputs
A map of inputs, one per stitched source. Populated by build().
property
out
Stitched image, ImgFrame of type BGR888i. Its transformation describes the virtual camera that rendered it, see the class documentation.
property
sync
Internal Sync node time-aligning the inputs.
class

depthai.beta.node.Stitching.Plane

class

depthai.beta.node.Stitching.VirtualCamera

class

depthai.beta.node.XFeatMonoParser(depthai.DeviceNode)

method
method
getInputSize(self) -> tuple[int, int]: tuple[int, int]
Returns the model input image size as (width, height).
method
getMaxKeypoints(self) -> int: int
Returns the maximum number of keypoints to keep per frame.
method
getOriginalSize(self) -> tuple[int, int]|None: tuple[int, int]|None
Returns the original image size as (width, height), or std::nullopt when not configured.
method
getOutputLayerFeats(self) -> str: str
Returns the name of the output layer containing the feature map.
method
getOutputLayerHeatmaps(self) -> str: str
Returns the name of the output layer containing the reliability heat map.
method
getOutputLayerKeypoints(self) -> str: str
Returns the name of the output layer containing the keypoint logits.
method
runOnHost(self) -> bool: bool
Check if the node is set to run on host.
method
setInputSize(self, width: int, height: int)
Sets the model input image size the keypoint positions are decoded in.  Defaults to 640x352 like the source parser. Configuring from a full NNArchive takes it from the head metadata or derives it from the model input's declared shape and layout; the most recent configuration wins.  Parameter ``width``:     Input image width, must be greater than 0  Parameter ``height``:     Input image height, must be greater than 0
method
setMaxKeypoints(self, maxKeypoints: int)
Sets the maximum number of keypoints to keep per frame.  Parameter ``maxKeypoints``:     Maximum number of keypoints @note Configures startup behavior. Send     XFeatMonoParserConfig to inputConfig after the pipeline starts.
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one XFeatMonoParser head; use setNNArchiveHead() to select a specific head from a multi-head archive. When the head metadata carries no input size, the input size is derived from the model input's declared shape and layout (NHWC or NCHW).  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be an XFeatMonoParser head with exactly three output layers; the layer whose name contains "feats" is used as the feature map layer, the layer whose name contains "keypoints" as the keypoint logit layer and the layer whose name contains "heatmaps" as the reliability heat map layer. The original size, input size and maximum keypoint count are read from the head metadata keys original_size, input_size and max_keypoints; missing keys keep the current values.  Parameter ``head:``:     NNArchive head to set
method
setOriginalSize(self, width: int, height: int)
Sets the original image size the emitted keypoint positions are scaled to.  Must be configured before the pipeline starts, either explicitly or through head metadata.  Parameter ``width``:     Original image width, must be greater than 0  Parameter ``height``:     Original image height, must be greater than 0
method
setOutputLayerFeats(self, outputLayerFeats: str)
Sets the name of the output layer containing the feature map.  Parameter ``outputLayerFeats``:     Name of the output layer containing the feature map
method
setOutputLayerHeatmaps(self, outputLayerHeatmaps: str)
Sets the name of the output layer containing the reliability heat map.  Parameter ``outputLayerHeatmaps``:     Name of the output layer containing the reliability heat map
method
setOutputLayerKeypoints(self, outputLayerKeypoints: str)
Sets the name of the output layer containing the keypoint logits.  Parameter ``outputLayerKeypoints``:     Name of the output layer containing the keypoint logits
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device. By default, the node runs on the device.
method
setTrigger(self)
Requests the reference frame update: after the next decoded frame's message is emitted, that frame's keypoints become the reference the following frames are matched against. May be called at any time while the pipeline runs.
property
initialConfig
Configuration used until a message is received on inputConfig.
property
input
Input NN results with XFeat data to parse.
property
inputConfig
Runtime parser configuration. When synchronized, one configuration is consumed per frame; otherwise all queued configurations are drained and the newest valid one is used.
property
out
Outputs TrackedFeatures message with the matched keypoint pairs.
class

depthai.beta.node.XFeatStereoParser(depthai.DeviceNode)

method
method
getInputSize(self) -> tuple[int, int]: tuple[int, int]
Returns the model input image size as (width, height).
method
getMaxKeypoints(self) -> int: int
Returns the maximum number of keypoints to keep per frame.
method
getOriginalSize(self) -> tuple[int, int]|None: tuple[int, int]|None
Returns the original image size as (width, height), or std::nullopt when not configured.
method
getOutputLayerFeats(self) -> str: str
Returns the name of the output layer containing the feature map.
method
getOutputLayerHeatmaps(self) -> str: str
Returns the name of the output layer containing the reliability heat map.
method
getOutputLayerKeypoints(self) -> str: str
Returns the name of the output layer containing the keypoint logits.
method
runOnHost(self) -> bool: bool
Check if the node is set to run on host.
method
setInputSize(self, width: int, height: int)
Sets the model input image size the keypoint positions are decoded in.  Defaults to 640x352 like the source parser. Configuring from a full NNArchive takes it from the head metadata or derives it from the model input's declared shape and layout; the most recent configuration wins.  Parameter ``width``:     Input image width, must be greater than 0  Parameter ``height``:     Input image height, must be greater than 0
method
setMaxKeypoints(self, maxKeypoints: int)
Sets the maximum number of keypoints to keep per frame.  Parameter ``maxKeypoints``:     Maximum number of keypoints @note Configures startup behavior. Send     XFeatStereoParserConfig to inputConfig after the pipeline starts.
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one XFeatStereoParser head; use setNNArchiveHead() to select a specific head from a multi-head archive. When the head metadata carries no input size, the input size is derived from the model input's declared shape and layout (NHWC or NCHW).  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be an XFeatStereoParser head with exactly three output layers; the layer whose name contains "feats" is used as the feature map layer, the layer whose name contains "keypoints" as the keypoint logit layer and the layer whose name contains "heatmaps" as the reliability heat map layer. The original size, input size and maximum keypoint count are read from the head metadata keys original_size, input_size and max_keypoints; missing keys keep the current values.  Parameter ``head:``:     NNArchive head to set
method
setOriginalSize(self, width: int, height: int)
Sets the original image size the emitted keypoint positions are scaled to.  Must be configured before the pipeline starts, either explicitly or through head metadata.  Parameter ``width``:     Original image width, must be greater than 0  Parameter ``height``:     Original image height, must be greater than 0
method
setOutputLayerFeats(self, outputLayerFeats: str)
Sets the name of the output layer containing the feature map.  Parameter ``outputLayerFeats``:     Name of the output layer containing the feature map
method
setOutputLayerHeatmaps(self, outputLayerHeatmaps: str)
Sets the name of the output layer containing the reliability heat map.  Parameter ``outputLayerHeatmaps``:     Name of the output layer containing the reliability heat map
method
setOutputLayerKeypoints(self, outputLayerKeypoints: str)
Sets the name of the output layer containing the keypoint logits.  Parameter ``outputLayerKeypoints``:     Name of the output layer containing the keypoint logits
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device. By default, the node runs on the device.
property
initialConfig
Configuration used until a message is received on inputConfig.
property
inputConfig
Runtime parser configuration. When synchronized, one configuration is consumed per frame pair; otherwise all queued configurations are drained and the newest valid one is used.
property
out
Outputs TrackedFeatures message with the matched keypoint pairs.
property
referenceInput
Input NN results of the reference source (e.g. the left camera) with XFeat data to parse.
property
targetInput
Input NN results of the target source (e.g. the right camera) with XFeat data to parse.
class

depthai.beta.node.YuNetParser(depthai.DeviceNode)

method
method
getConfidenceThreshold(self) -> float: float
Returns the confidence score threshold for detected faces.
method
getInputSize(self) -> tuple[int, int]|None: tuple[int, int]|None
Returns the model input image size as (width, height), or std::nullopt when it is not set.
method
getIouThreshold(self) -> float: float
Returns the non-maximum suppression (IoU) threshold.
method
getLabelNames(self) -> list[str]: list[str]
Returns the label names for the detected faces.
method
getMaxDetections(self) -> int: int
Returns the maximum number of detections to keep.
method
getOutputLayerConf(self) -> str: str
Returns the name of the output layer containing the confidence predictions.
method
getOutputLayerIou(self) -> str: str
Returns the name of the output layer containing the IoU predictions.
method
getOutputLayerLoc(self) -> str: str
Returns the name of the output layer containing the location predictions.
method
runOnHost(self) -> bool: bool
Check if the node is set to run on host.
method
setConfidenceThreshold(self, threshold: float)
Sets the confidence score threshold for detected faces. Detections with a score strictly greater than the threshold are kept.  Parameter ``threshold``:     Confidence score threshold @note Configures startup behavior. Send     YuNetParserConfig to inputConfig after the pipeline starts.
method
setInputSize(self, width: int, height: int)
Sets the model input image size the anchors are computed against and the emitted coordinates are normalized by. Unset by default; it must be configured from an NNArchive or with this setter before the parser processes messages.  Configuring from a full NNArchive derives it from the model input's declared shape and layout; the most recent configuration wins.  Parameter ``width``:     Input image width, must be greater than 0  Parameter ``height``:     Input image height, must be greater than 0
method
setIouThreshold(self, threshold: float)
Sets the non-maximum suppression (IoU) threshold. Candidates whose overlap with a kept detection is at most the threshold (inclusive) survive suppression.  Parameter ``threshold``:     Non-maximum suppression threshold @note Configures startup behavior. Send     YuNetParserConfig to inputConfig after the pipeline starts.
method
setLabelNames(self, labelNames: list[str])
Sets the label names for the detected faces. The first label name is assigned to every detection (all detections carry label 0). When empty, no label name is assigned. Defaults to ("Face").  Parameter ``labelNames``:     List of label names
method
setMaxDetections(self, maxDetections: int)
Sets the maximum number of detections to keep, applied as the non-maximum suppression top-k limit (no limit when 0 or negative).  Parameter ``maxDetections``:     Maximum number of detections to keep @note Configures startup behavior. Send     YuNetParserConfig to inputConfig after the pipeline starts.
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. The archive must contain exactly one YuNetParser head and exactly one model input; use setNNArchiveHead() to select a specific head from a multi-head archive. The input size is derived from the model input's declared shape and layout (NHWC or NCHW).  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node. The head must be a YuNetParser head; every head output layer name must contain "loc", "conf" or "iou" and is routed to the matching output layer name setting.  Parameter ``head:``:     NNArchive head to set @note A head carries no model input metadata, so the     input size keeps its current value; configure it with setInputSize() when it     is not set yet.
method
setOutputLayerConf(self, confOutputLayerName: str)
Sets the name of the output layer containing the confidence predictions. When left empty, the name is auto-detected from the incoming NNData as the single layer name starting with "conf".  Parameter ``confOutputLayerName``:     Output layer name for the conf tensor
method
setOutputLayerIou(self, iouOutputLayerName: str)
Sets the name of the output layer containing the IoU predictions. When left empty, the name is auto-detected from the incoming NNData as the single layer name starting with "iou".  Parameter ``iouOutputLayerName``:     Output layer name for the IoU tensor
method
setOutputLayerLoc(self, locOutputLayerName: str)
Sets the name of the output layer containing the location predictions. When left empty, the name is auto-detected from the incoming NNData as the single layer name starting with "loc".  Parameter ``locOutputLayerName``:     Output layer name for the loc tensor
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device. By default, the node runs on the device.
property
initialConfig
Configuration used when the parser starts.
property
input
Input NN results with YuNet detection data to parse.
property
inputConfig
Runtime parser configuration. In synchronized mode one configuration is consumed per input frame; otherwise all queued configurations are drained and the newest valid one is retained.
property
out
Outputs ImgDetections message with the bounding boxes, labels, confidence scores and keypoints of the detected faces.
class

depthai.beta.Classifications(depthai.Buffer, depthai.Transformable)

method
method
method
getTopClass(self) -> str: str
Returns the most probable class name.  Assumes the classes are sorted in descending order of score, which holds for parser-emitted messages.  Throws:     std::runtime_error if the message contains no classes.
method
getTopScore(self) -> float: float
Returns the score of the most probable class.  Assumes the scores are sorted in descending order, which holds for parser- emitted messages.  Throws:     std::runtime_error if the message contains no scores.
method
getVisualizationMessage(self) -> depthai.ImgAnnotations|depthai.ImgFrame|None: depthai.ImgAnnotations|depthai.ImgFrame|None
Returns an ImgAnnotations visualization with up to the top five classes and their scores, or std::monostate when no transformation metadata is available to derive the annotation layout from.
method
transformTo(self, target: depthai.ImgTransformation) -> Classifications: Classifications
Returns a new Classifications message with the transformation metadata replaced by the target transformation. Classification results carry no spatial data, so classes and scores are unchanged.  Parameter ``target``:     Target image transformation.
property
classes
Class names, index-aligned with the scores vector.
method
property
scores
Classification scores, index-aligned with the classes vector.
method
class

depthai.beta.Cluster

method
property
label
Label of the cluster.
method
property
points
Points in the cluster.
method
class

depthai.beta.Clusters(depthai.Buffer, depthai.Transformable)

method
method
method
getVisualizationMessage(self) -> depthai.ImgAnnotations|depthai.ImgFrame|None: depthai.ImgAnnotations|depthai.ImgFrame|None
Returns an ImgAnnotations visualization with each cluster drawn as points in a distinct color sampled from a rainbow colormap.  Throws:     std::runtime_error if the message contains more than 255 clusters.
method
transformTo(self, target: depthai.ImgTransformation) -> Clusters: Clusters
Returns a new Clusters message with the cluster point image coordinates remapped from this message's transformation into the target transformation.  Parameter ``target``:     Target image transformation.  Throws:     std::runtime_error if this message carries no transformation metadata.
property
clusters
Detected clusters of points.
method
class

depthai.beta.Keypoints(depthai.Buffer, depthai.Transformable)

method
method
method
method
method
getPoints2f(self) -> depthai.VectorPoint2f: depthai.VectorPoint2f
Returns the 2D image coordinates of the keypoints, dropping the z axis values.
method
getPoints3f(self) -> list[depthai.Point3f]: list[depthai.Point3f]
Returns the 3D image coordinates of the keypoints. 2D keypoints carry a z coordinate of 0.
method
getVisualizationMessage(self) -> depthai.ImgAnnotations|depthai.ImgFrame|None: depthai.ImgAnnotations|depthai.ImgFrame|None
Returns an ImgAnnotations visualization with the keypoints drawn as points and the skeleton edges drawn as lines.
method
setEdges(self, edges: list[typing.Annotated[list[int], pybind11_stubgen.typing_ext.FixedSize(2)]])
Sets the skeleton edges.  Parameter ``edges``:     Pairs of keypoint indices to connect.  Throws:     std::invalid_argument if an edge index is out of range or an edge is a self-     loop.
method
method
transformTo(self, target: depthai.ImgTransformation) -> Keypoints: Keypoints
Returns a new Keypoints message with the keypoint image coordinates remapped from this message's transformation into the target transformation.  Parameter ``target``:     Target image transformation.  Throws:     std::runtime_error if this message carries no transformation metadata.
property
keypointsList
Native keypoints list carrying the keypoints and the skeleton edges connecting them.
method
class

depthai.beta.Line

method
property
confidence
Confidence of the line, in [0, 1].
method
property
endPoint
End point of the line with x and y coordinate.
method
property
startPoint
Start point of the line with x and y coordinate.
method
class

depthai.beta.Lines(depthai.Buffer, depthai.Transformable)

method
method
method
getVisualizationMessage(self) -> depthai.ImgAnnotations|depthai.ImgFrame|None: depthai.ImgAnnotations|depthai.ImgFrame|None
Returns an ImgAnnotations visualization with each line drawn as a two-point line strip.
method
transformTo(self, target: depthai.ImgTransformation) -> Lines: Lines
Returns a new Lines message with the line point image coordinates remapped from this message's transformation into the target transformation.  Parameter ``target``:     Target image transformation.  Throws:     std::runtime_error if this message carries no transformation metadata.
property
lines
Detected lines.
method
class

depthai.beta.Map2D(depthai.Buffer, depthai.Transformable)

method
method
method
getHeight(self) -> int: int
Returns the height of the 2D map.
method
getMap(self) -> numpy.ndarray[numpy.float32]: numpy.ndarray[numpy.float32]
Returns a copy of the 2D map values in row-major order. If no map is set, returns an empty vector.
method
getVisualizationMessage(self) -> depthai.ImgAnnotations|depthai.ImgFrame|None: depthai.ImgAnnotations|depthai.ImgFrame|None
Returns an ImgFrame visualization of the map colored with a plasma colormap.  When any map value is below 1 the values are scaled by 255, so maps normalized to [0, 1] use the full colormap range. The values are then truncated to 8-bit indices into the colormap and emitted as an interleaved BGR frame.
method
getWidth(self) -> int: int
Returns the width of the 2D map.
method
setMap(self, map: numpy.ndarray)
Sets the 2D map. The values are copied into the buffer payload.  Parameter ``map``:     Map values in row-major order, of size width * height.  Parameter ``width``:     Map width in values per row.  Parameter ``height``:     Map height in rows.  Throws:     std::runtime_error if the map size does not equal width * height.
method
transformTo(self, target: depthai.ImgTransformation) -> Map2D: Map2D
Returns a new Map2D message with the transformation metadata replaced by the target transformation. The map values and dimensions are unchanged.  Parameter ``target``:     Target image transformation.  Throws:     std::runtime_error if this message carries no transformation metadata.
class

depthai.beta.Prediction

method
property
prediction
The predicted value.
method
class

depthai.beta.Predictions(depthai.Buffer, depthai.Transformable)

method
method
method
getFirstPrediction(self) -> float: float
Returns the first predicted value. Useful for single-prediction models.  Throws:     std::runtime_error if the message contains no predictions.
method
getVisualizationMessage(self) -> depthai.ImgAnnotations|depthai.ImgFrame|None: depthai.ImgAnnotations|depthai.ImgFrame|None
Returns an ImgAnnotations visualization with each predicted value drawn as text, one below the other, or std::monostate when no transformation metadata is available to derive the annotation layout from.
method
transformTo(self, target: depthai.ImgTransformation) -> Predictions: Predictions
Returns a new Predictions message with the transformation metadata replaced by the target transformation. Regression results carry no spatial data, so the predictions are unchanged.  Parameter ``target``:     Target image transformation.
property
predictions
Predicted values, in the order the model emitted them.
method
class

depthai.beta.MultiDeviceCalibrationControl.Commands

class
class
class
class

depthai.beta.MultiDeviceCalibrationControl.Commands.Start

class

depthai.beta.MultiDeviceCalibrationControl.Commands.Stop

class

depthai.beta.MultiDeviceCalibrationControl.Commands.Reset

class

depthai.beta.MultiDeviceCalibrationResult(depthai.Buffer)

variable
variable
variable
variable
variable
method
method
getHandler(self) -> ...|None: ...|None
Build a MultiDeviceCalibrationHandler from the calibration graph.  Returns:     The handler when the result carries a graph, or std::nullopt when it does     not.
class

depthai.beta.ClassificationSequenceParserConfig(depthai.Buffer)

variable
variable
variable
method
method
method
getConcatenateClasses(self) -> bool: bool
Gets whether decoded class labels are concatenated.  Returns:     Whether class labels are concatenated
method
getIgnoredIndexes(self) -> list[int]: list[int]
Gets the class indexes ignored while decoding the sequence.  Returns:     Ignored class indexes
method
getRemoveDuplicates(self) -> bool: bool
Gets whether consecutive duplicate classes are removed.  Returns:     Whether duplicate classes are removed
method
setConcatenateClasses(self, enabled: bool)
Sets whether decoded class labels are concatenated.  Parameter ``concatenateClasses``:     Whether class labels are concatenated
method
setIgnoredIndexes(self, indexes: list[int])
Sets the class indexes ignored while decoding the sequence.  Parameter ``indexes``:     Nonnegative class indexes to ignore
method
setRemoveDuplicates(self, enabled: bool)
Sets whether consecutive duplicate classes are removed.  Parameter ``removeDuplicates``:     Whether duplicate classes are removed
method
validate(self) -> bool: bool
Validates this configuration.  Returns:     True if all ignored indexes are nonnegative
class

depthai.beta.FastSAMParserConfig(depthai.Buffer)

class
Prompt
Prompt mode used to select emitted segmentation masks.  Members:    EVERYTHING : Keep all detected instances.    POINT : Select instances using a point and point label.    BOUNDING_BOX : Select an instance using a bounding box.
variable
variable
variable
variable
variable
variable
variable
method
method
method
method
getConfidenceThreshold(self) -> float: float
Gets the minimum detection confidence.  Returns:     Confidence threshold
method
getIouThreshold(self) -> float: float
Gets the intersection-over-union threshold.  Returns:     IoU threshold
method
getMaskConfidence(self) -> float: float
Gets the threshold used to binarize instance masks.  Returns:     Mask confidence threshold
method
getPointLabel(self) -> int|None: int|None
Gets the prompt point label.  Returns:     Optional point label
method
getPoints(self) -> tuple[int, int]|None: tuple[int, int]|None
Gets the prompt point.  Returns:     Optional prompt point as (x, y)
method
method
setBoundingBox(self, boundingBox: typing.Annotated[list[int], pybind11_stubgen.typing_ext.FixedSize(4)])
Sets the prompt bounding box.  Parameter ``boundingBox``:     Bounding box as {x1, y1, x2, y2}, with ordered coordinates and positive     x2/y2
method
setConfidenceThreshold(self, threshold: float)
Sets the minimum detection confidence.  Parameter ``threshold``:     Confidence threshold in the range [0, 1]
method
setIouThreshold(self, threshold: float)
Sets the intersection-over-union threshold used by non-maximum suppression.  Parameter ``threshold``:     IoU threshold in the range [0, 1]
method
setMaskConfidence(self, threshold: float)
Sets the threshold used to binarize instance masks.  Parameter ``threshold``:     Mask confidence threshold in the range [0, 1]
method
setPointLabel(self, label: int)
Sets the prompt point label.  Parameter ``label``:     Point label, 0 for negative or 1 for positive
method
setPoints(self, x: int, y: int)
Sets the prompt point.  Parameter ``x``:     Point x coordinate  Parameter ``y``:     Point y coordinate
method
setPrompt(self, prompt: FastSAMParserConfig.Prompt)
Sets the prompt mode. Required point or bounding-box data must already be present.  Parameter ``prompt``:     Prompt mode
method
validate(self) -> bool: bool
Validates thresholds, prompt payload, point label, and bounding-box coordinates.  Returns:     True if the complete configuration is valid
class

depthai.beta.HRNetParserConfig(depthai.Buffer)

variable
method
method
method
getScoreThreshold(self) -> float: float
Gets the minimum keypoint score.  Returns:     Score threshold
method
setScoreThreshold(self, threshold: float)
Sets the minimum keypoint score.  Parameter ``threshold``:     Score threshold in the range [0, 1]
method
validate(self) -> bool: bool
Validates this configuration.  Returns:     True if the score threshold is in the range [0, 1]
class

depthai.beta.MLSDParserConfig(depthai.Buffer)

variable
variable
variable
method
method
method
getDistanceThreshold(self) -> float: float
Gets the distance threshold used while decoding line segments.  Returns:     Distance threshold
method
getScoreThreshold(self) -> float: float
Gets the minimum candidate score.  Returns:     Score threshold
method
getTopK(self) -> int: int
Gets the number of highest-scoring candidates retained for decoding.  Returns:     Candidate count
method
setDistanceThreshold(self, threshold: float)
Sets the distance threshold used while decoding line segments.  Parameter ``threshold``:     Nonnegative distance threshold
method
setScoreThreshold(self, threshold: float)
Sets the minimum candidate score.  Parameter ``threshold``:     Score threshold in the range [0, 1]
method
setTopK(self, topK: int)
Sets the number of highest-scoring candidates retained for decoding.  Parameter ``topK``:     Positive candidate count
method
validate(self) -> bool: bool
Validates this configuration.  Returns:     True if topK is positive, the score threshold is in [0, 1], and the distance     threshold is nonnegative
class

depthai.beta.MPPalmDetectionParserConfig(depthai.Buffer)

variable
variable
variable
method
method
method
getConfidenceThreshold(self) -> float: float
Gets the minimum detection confidence.  Returns:     Confidence threshold
method
getIouThreshold(self) -> float: float
Gets the intersection-over-union threshold.  Returns:     IoU threshold
method
getMaxDetections(self) -> int: int
Gets the maximum number of emitted detections.  Returns:     Maximum detection count
method
setConfidenceThreshold(self, threshold: float)
Sets the minimum detection confidence.  Parameter ``threshold``:     Confidence threshold in the range [0, 1]
method
setIouThreshold(self, threshold: float)
Sets the intersection-over-union threshold used by non-maximum suppression.  Parameter ``threshold``:     IoU threshold in the range [0, 1]
method
setMaxDetections(self, maxDetections: int)
Sets the maximum number of emitted detections.  Parameter ``maxDetections``:     Positive maximum detection count
method
validate(self) -> bool: bool
Validates this configuration.  Returns:     True if both thresholds are in [0, 1] and maxDetections is positive
class

depthai.beta.MapOutputParserConfig(depthai.Buffer)

variable
method
method
method
getMinMaxScaling(self) -> bool: bool
Gets whether output values are scaled using their minimum and maximum.  Returns:     Whether min-max scaling is enabled
method
setMinMaxScaling(self, enabled: bool)
Sets whether output values are scaled using their minimum and maximum.  Parameter ``enabled``:     Whether min-max scaling is enabled
method
validate(self) -> bool: bool
Validates this configuration.  Returns:     True because every value of the boolean option is valid
class

depthai.beta.PPTextDetectionParserConfig(depthai.Buffer)

variable
variable
variable
method
method
method
getConfidenceThreshold(self) -> float: float
Gets the minimum detection confidence.  Returns:     Confidence threshold
method
getMaskThreshold(self) -> float: float
Gets the threshold applied to the text probability mask.  Returns:     Mask threshold
method
getMaxDetections(self) -> int: int
Gets the maximum number of emitted detections.  Returns:     Maximum detection count
method
setConfidenceThreshold(self, threshold: float)
Sets the minimum detection confidence.  Parameter ``threshold``:     Confidence threshold in the range [0, 1]
method
setMaskThreshold(self, threshold: float)
Sets the threshold applied to the text probability mask.  Parameter ``threshold``:     Mask threshold in the range [0, 1]
method
setMaxDetections(self, maxDetections: int)
Sets the maximum number of emitted detections.  Parameter ``maxDetections``:     Positive maximum detection count
method
validate(self) -> bool: bool
Validates this configuration.  Returns:     True if both thresholds are in [0, 1] and maxDetections is positive
class

depthai.beta.RFDETRParserConfig(depthai.Buffer)

variable
variable
variable
method
method
method
getConfidenceThreshold(self) -> float: float
Get the minimum detection confidence.  Returns:     Confidence threshold in the inclusive range [0, 1]
method
getMaskConfidence(self) -> float: float
Get the minimum per-pixel confidence used when creating instance masks.  Returns:     Mask confidence threshold in the inclusive range [0, 1]
method
getMaxDetections(self) -> int: int
Get the maximum number of detections to retain.  Returns:     Maximum detection count
method
setConfidenceThreshold(self, threshold: float)
Set the minimum detection confidence.  Parameter ``threshold``:     Confidence threshold in the inclusive range [0, 1]
method
setMaskConfidence(self, threshold: float)
Set the minimum per-pixel confidence used when creating instance masks.  Parameter ``threshold``:     Mask confidence threshold in the inclusive range [0, 1]
method
setMaxDetections(self, maxDetections: int)
Set the maximum number of detections to retain.  Parameter ``maxDetections``:     Maximum detection count, which must be positive
method
validate(self) -> bool: bool
Check whether all configuration values are valid.  Returns:     True when both confidence thresholds are in the inclusive range [0, 1] and     maxDetections is positive
class

depthai.beta.SCRFDParserConfig(depthai.Buffer)

variable
variable
variable
method
method
method
getConfidenceThreshold(self) -> float: float
Get the minimum detection confidence.  Returns:     Confidence threshold in the inclusive range [0, 1]
method
getIouThreshold(self) -> float: float
Get the non-maximum suppression intersection-over-union threshold.  Returns:     Intersection-over-union threshold in the inclusive range [0, 1]
method
getMaxDetections(self) -> int: int
Get the maximum number of post-suppression detections to retain.  Returns:     Maximum post-suppression detection count
method
setConfidenceThreshold(self, threshold: float)
Set the minimum detection confidence.  Parameter ``threshold``:     Confidence threshold in the inclusive range [0, 1]
method
setIouThreshold(self, threshold: float)
Set the non-maximum suppression intersection-over-union threshold.  Parameter ``threshold``:     Intersection-over-union threshold in the inclusive range [0, 1]
method
setMaxDetections(self, maxDetections: int)
Set the maximum number of post-suppression detections to retain.  Parameter ``maxDetections``:     Maximum detection count, which must be positive
method
validate(self) -> bool: bool
Check whether all configuration values are valid.  Returns:     True when both thresholds are in the inclusive range [0, 1] and     maxDetections is positive
class

depthai.beta.SuperAnimalParserConfig(depthai.Buffer)

variable
method
method
method
getScoreThreshold(self) -> float: float
Get the minimum keypoint score.  Returns:     Score threshold in the inclusive range [0, 1]
method
setScoreThreshold(self, threshold: float)
Set the minimum keypoint score.  Parameter ``threshold``:     Score threshold in the inclusive range [0, 1]
method
validate(self) -> bool: bool
Check whether all configuration values are valid.  Returns:     True when scoreThreshold is in the inclusive range [0, 1]
class

depthai.beta.XFeatMonoParserConfig(depthai.Buffer)

variable
method
method
method
getMaxKeypoints(self) -> int: int
Get the maximum number of keypoints to retain per frame.  Returns:     Maximum keypoint count
method
setMaxKeypoints(self, maxKeypoints: int)
Set the maximum number of keypoints to retain per frame.  Parameter ``maxKeypoints``:     Maximum keypoint count, which must be positive
method
validate(self) -> bool: bool
Check whether all configuration values are valid.  Returns:     True when maxKeypoints is positive
class

depthai.beta.XFeatStereoParserConfig(depthai.Buffer)

variable
method
method
method
getMaxKeypoints(self) -> int: int
Get the maximum number of keypoints to retain from each frame in the stereo pair.  Returns:     Maximum keypoint count applied to each frame
method
setMaxKeypoints(self, maxKeypoints: int)
Set the maximum number of keypoints to retain from each frame in the stereo pair.  Parameter ``maxKeypoints``:     Maximum keypoint count, which must be positive
method
validate(self) -> bool: bool
Check whether all configuration values are valid.  Returns:     True when maxKeypoints is positive
class

depthai.beta.YuNetParserConfig(depthai.Buffer)

variable
variable
variable
method
method
method
getConfidenceThreshold(self) -> float: float
Get the minimum face detection confidence.  Returns:     Confidence threshold in the inclusive range [0, 1]
method
getIouThreshold(self) -> float: float
Get the non-maximum suppression intersection-over-union threshold.  Returns:     Intersection-over-union threshold in the inclusive range [0, 1]
method
getMaxDetections(self) -> int: int
Get the maximum number of detections to retain.  Returns:     Maximum detection count; a value less than or equal to zero means unlimited
method
setConfidenceThreshold(self, threshold: float)
Set the minimum face detection confidence.  Parameter ``threshold``:     Confidence threshold in the inclusive range [0, 1]
method
setIouThreshold(self, threshold: float)
Set the non-maximum suppression intersection-over-union threshold.  Parameter ``threshold``:     Intersection-over-union threshold in the inclusive range [0, 1]
method
setMaxDetections(self, maxDetections: int)
Set the maximum number of detections to retain.  Parameter ``maxDetections``:     Maximum detection count; a value less than or equal to zero means unlimited
method
validate(self) -> bool: bool
Check whether all configuration values are valid.  Returns:     True when confidenceThreshold and iouThreshold are in the inclusive range     [0, 1]; maxDetections may have any integer value
class

depthai.beta.ClassificationSequenceParserProperties

class

depthai.beta.FastSAMParserProperties

class

depthai.beta.ImgDetectionsFilterProperties

class

depthai.beta.MapOutputParserProperties

class

depthai.beta.MLSDParserProperties

class

depthai.beta.MPPalmDetectionParserProperties

class

depthai.beta.PPTextDetectionParserProperties

class

depthai.beta.MultiDeviceCalibrationHandler

static method
method
method
getDeviceSocket(self, deviceId: str) -> depthai.CameraBoardSocket|None: depthai.CameraBoardSocket|None
Get the local calibration-origin socket used by a device in the graph.  Returns:     The socket when the device participates in the graph, or std::nullopt when     it does not.
method
getExtrinsicsToOrigin(self, deviceId: str, localOriginSocket: depthai.CameraBoardSocket) -> depthai.Extrinsics|None: depthai.Extrinsics|None
Get the transform from a device's local calibration origin to its connected component's automatically selected origin.  Returns:     A meter-normalized transform when the device participates in the graph, or     std::nullopt when it does not.  Throws:     std::invalid_argument when the graph is invalid or the supplied local socket     does not match the graph.
method
method
toJson(self) -> json: json
Return the handler's JSON representation with translations in centimeters.
method
toJsonFile(self, destPath: os.PathLike) -> bool: bool
Write the handler's centimeter-normalized JSON representation to a file.
package

depthai.filters

module
params
Parameters for filters
module

depthai.filters.params

class
MedianFilter
Members:    MEDIAN_OFF    KERNEL_3x3    KERNEL_5x5    KERNEL_7x7
class
class
TemporalFilter
Temporal filtering with optional persistence.
class
ThresholdFilter
Threshold filtering. Filters out distances outside of a given interval.
class
class

depthai.filters.params.SpatialFilter

method
method
property
alpha
The Alpha factor in an exponential moving average with Alpha=1 - no filter. Alpha = 0 - infinite filter. Determines the amount of smoothing.
method
property
delta
Step-size boundary. Establishes the threshold used to preserve "edges". If the disparity value between neighboring pixels exceed the disparity threshold set by this delta parameter, then filtering will be temporarily disabled. Default value 0 means auto: 3 disparity integer levels. In case of subpixel mode it's 3*number of subpixel levels.
method
property
enable
Whether to enable or disable the filter.
method
property
holeFillingRadius
An in-place heuristic symmetric hole-filling mode applied horizontally during the filter passes. Intended to rectify minor artefacts with minimal performance impact. Search radius for hole filling.
method
property
numIterations
Number of iterations over the image in both horizontal and vertical direction.
method
class

depthai.filters.params.TemporalFilter

class
PersistencyMode
Persistency algorithm type.  Members:    PERSISTENCY_OFF :     VALID_8_OUT_OF_8 :     VALID_2_IN_LAST_3 :     VALID_2_IN_LAST_4 :     VALID_2_OUT_OF_8 :     VALID_1_IN_LAST_2 :     VALID_1_IN_LAST_5 :     VALID_1_IN_LAST_8 :     PERSISTENCY_INDEFINITELY : 
method
method
property
alpha
The Alpha factor in an exponential moving average with Alpha=1 - no filter. Alpha = 0 - infinite filter. Determines the extent of the temporal history that should be averaged.
method
property
delta
Step-size boundary. Establishes the threshold used to preserve surfaces (edges). If the disparity value between neighboring pixels exceed the disparity threshold set by this delta parameter, then filtering will be temporarily disabled. Default value 0 means auto: 3 disparity integer levels. In case of subpixel mode it's 3*number of subpixel levels.
method
property
enable
Whether to enable or disable the filter.
method
property
persistencyMode
Persistency mode. If the current disparity/depth value is invalid, it will be replaced by an older value, based on persistency mode.
method
class

depthai.filters.params.ThresholdFilter

method
method
property
maxRange
Maximum range in depth units. Depth values over this value are invalidated.
method
property
minRange
Minimum range in depth units. Depth values under this value are invalidated.
method
class

depthai.filters.params.SpeckleFilter

method
method
property
differenceThreshold
Maximum difference between neighbor disparity pixels to put them into the same blob. Units in disparity integer levels.
method
property
enable
Whether to enable or disable the filter.
method
property
speckleRange
Speckle search range.
method
module

depthai.modelzoo

function
getDefaultCachePath() -> os.PathLike: os.PathLike
Get the default cache path (where models are cached)
function
getDefaultModelsPath() -> os.PathLike: os.PathLike
Get the default models path (where yaml files are stored)
function
getDownloadEndpoint() -> str: str
Get the download endpoint (for model querying)
function
getHealthEndpoint() -> str: str
Get the health endpoint (for internet check)
function
setDefaultCachePath(path: os.PathLike)
Set the default cache path (where models are cached)  Parameter ``path``:
function
setDefaultModelsPath(path: os.PathLike)
Set the default models path (where yaml files are stored)  Parameter ``path``:
function
setDownloadEndpoint(endpoint: str)
Set the download endpoint (for model querying)  Parameter ``endpoint``:
function
setHealthEndpoint(endpoint: str)
Set the health endpoint (for internet check)  Parameter ``endpoint``:
package

depthai.nn_archive

module
module

depthai.nn_archive.v1

class
Config
The main class of the multi/single-stage model config scheme (multi- stage models consists of interconnected single-stage models).  @type config_version: str @ivar config_version: String representing config schema version in format 'x.y' where x is major version and y is minor version @type model: Model @ivar model: A Model object representing the neural network used in the archive.
class
Model
A Model object representing the neural network used in the archive.  Class defining a single-stage model config scheme.  @type metadata: Metadata @ivar metadata: Metadata object defining the model metadata. @type inputs: list @ivar inputs: List of Input objects defining the model inputs. @type outputs: list @ivar outputs: List of Output objects defining the model outputs. @type heads: list @ivar heads: List of Head objects defining the model heads. If not defined, we assume a raw output.
class
Head
Represents head of a model.  @type name: str | None @ivar name: Optional name of the head. @type parser: str @ivar parser: Name of the parser responsible for processing the models output. @type outputs: List[str] | None @ivar outputs: Specify which outputs are fed into the parser. If None, all outputs are fed. @type metadata: C{HeadMetadata} | C{HeadObjectDetectionMetadata} | C{HeadClassificationMetadata} | C{HeadObjectDetectionSSDMetadata} | C{HeadSegmentationMetadata} | C{HeadYOLOMetadata} @ivar metadata: Metadata of the parser.
class
DataType
Data type of the input data (e.g., 'float32').  Represents all existing data types used in i/o streams of the model.  Precision of the model weights.  Data type of the output data (e.g., 'float32').  Members:    BOOLEAN    FLOAT16    FLOAT32    FLOAT64    INT4    INT8    INT16    INT32    INT64    UINT4    UINT8    UINT16    UINT32    UINT64    STRING
class
InputType
Members:    IMAGE    RAW
class
Input
Represents input stream of a model.  @type name: str @ivar name: Name of the input layer.  @type dtype: DataType @ivar dtype: Data type of the input data (e.g., 'float32').  @type input_type: InputType @ivar input_type: Type of input data (e.g., 'image').  @type shape: list @ivar shape: Shape of the input data as a list of integers (e.g. [H,W], [H,W,C], [N,H,W,C], ...).  @type layout: str @ivar layout: Lettercode interpretation of the input data dimensions (e.g., 'NCHW').  @type preprocessing: PreprocessingBlock @ivar preprocessing: Preprocessing steps applied to the input data.
class
Metadata
Metadata of the parser.  Metadata for the object detection head.  @type classes: list @ivar classes: Names of object classes detected by the model. @type n_classes: int @ivar n_classes: Number of object classes detected by the model. @type iou_threshold: float @ivar iou_threshold: Non-max supression threshold limiting boxes intersection. @type conf_threshold: float @ivar conf_threshold: Confidence score threshold above which a detected object is considered valid. @type max_det: int @ivar max_det: Maximum detections per image. @type anchors: list @ivar anchors: Predefined bounding boxes of different sizes and aspect ratios. The innermost lists are length 2 tuples of box sizes. The middle lists are anchors for each output. The outmost lists go from smallest to largest output.  Metadata for the classification head.  @type classes: list @ivar classes: Names of object classes classified by the model. @type n_classes: int @ivar n_classes: Number of object classes classified by the model. @type is_softmax: bool @ivar is_softmax: True, if output is already softmaxed  Metadata for the SSD object detection head.  @type boxes_outputs: str @ivar boxes_outputs: Output name corresponding to predicted bounding box coordinates. @type scores_outputs: str @ivar scores_outputs: Output name corresponding to predicted bounding box confidence scores.  Metadata for the segmentation head.  @type classes: list @ivar classes: Names of object classes segmented by the model. @type n_classes: int @ivar n_classes: Number of object classes segmented by the model. @type is_softmax: bool @ivar is_softmax: True, if output is already softmaxed @type background_class: bool | None @ivar background_class: True, if class index 0 is treated as background.  Metadata for the YOLO head.  @type yolo_outputs: list @ivar yolo_outputs: A list of output names for each of the different YOLO grid sizes. @type mask_outputs: list | None @ivar mask_outputs: A list of output names for each mask output. @type protos_outputs: str | None @ivar protos_outputs: Output name for the protos. @type keypoints_outputs: list | None @ivar keypoints_outputs: A list of output names for the keypoints. @type angles_outputs: list | None @ivar angles_outputs: A list of output names for the angles. @type subtype: str @ivar subtype: YOLO family decoding subtype (e.g. yolov5, yolov6, yolov7 etc.) @type n_prototypes: int | None @ivar n_prototypes: Number of prototypes per bbox in YOLO instance segmnetation. @type n_keypoints: int | None @ivar n_keypoints: Number of keypoints per bbox in YOLO keypoint detection. @type is_softmax: bool | None @ivar is_softmax: True, if output is already softmaxed in YOLO instance segmentation @type strides: list | None @ivar strides: Strides for each YOLO output.  Metadata for the basic head. It allows you to specify additional fields.  @type postprocessor_path: str | None @ivar postprocessor_path: Path to the postprocessor.
class
MetadataClass
Metadata object defining the model metadata.  Represents metadata of a model.  @type name: str @ivar name: Name of the model. @type path: str @ivar path: Relative path to the model executable.
class
Output
Represents output stream of a model.  @type name: str @ivar name: Name of the output layer. @type dtype: DataType @ivar dtype: Data type of the output data (e.g., 'float32').
class
PreprocessingBlock
Preprocessing steps applied to the input data.  Represents preprocessing operations applied to the input data.  @type mean: list | None @ivar mean: Mean values in channel order. Order depends on the order in which the model was trained on. @type scale: list | None @ivar scale: Standardization values in channel order. Order depends on the order in which the model was trained on. @type reverse_channels: bool | None @ivar reverse_channels: If True input to the model is RGB else BGR. @type interleaved_to_planar: bool | None @ivar interleaved_to_planar: If True input to the model is interleaved (NHWC) else planar (NCHW). @type dai_type: str | None @ivar dai_type: DepthAI input type which is read by DepthAI to automatically setup the pipeline.
class

depthai.nn_archive.v1.Config

method
property
configVersion
String representing config schema version in format 'x.y' where x is major version and y is minor version.
method
property
model
A Model object representing the neural network used in the archive.
method
class

depthai.nn_archive.v1.Model

method
property
heads
List of Head objects defining the model heads. If not defined, we assume a raw output.
method
property
inputs
List of Input objects defining the model inputs.
method
property
metadata
Metadata object defining the model metadata.
method
property
outputs
List of Output objects defining the model outputs.
method
class

depthai.nn_archive.v1.Head

method
property
metadata
Metadata of the parser.
method
property
name
Optional name of the head.
method
property
outputs
Specify which outputs are fed into the parser. If None, all outputs are fed.
method
property
parser
Name of the parser responsible for processing the models output.
method
class

depthai.nn_archive.v1.Input

method
property
dtype
Data type of the input data (e.g., 'float32').
method
property
inputType
Type of input data (e.g., 'image').
method
property
layout
Lettercode interpretation of the input data dimensions (e.g., 'NCHW')
method
property
name
Name of the input layer.
method
property
preprocessing
Preprocessing steps applied to the input data.
method
property
shape
Shape of the input data as a list of integers (e.g. [H,W], [H,W,C], [N,H,W,C], ...).
method
class

depthai.nn_archive.v1.Metadata

method
property
anchors
Predefined bounding boxes of different sizes and aspect ratios. The innermost lists are length 2 tuples of box sizes. The middle lists are anchors for each output. The outmost lists go from smallest to largest output.
method
property
anglesOutputs
A list of output names for the angles.
method
property
backgroundClass
True, if class index 0 is treated as background.
method
property
boxesOutputs
Output name corresponding to predicted bounding box coordinates.
method
property
classes
Names of object classes recognized by the model.
method
property
confThreshold
Confidence score threshold above which a detected object is considered valid.
method
property
extraParams
Additional parameters
method
property
iouThreshold
Non-max supression threshold limiting boxes intersection.
method
property
isSoftmax
True, if output is already softmaxed.  True, if output is already softmaxed in YOLO instance segmentation.
method
property
keypointsOutputs
A list of output names for the keypoints.
method
property
maskOutputs
A list of output names for each mask output.
method
property
maxDet
Maximum detections per image.
method
property
nClasses
Number of object classes recognized by the model.
method
property
nKeypoints
Number of keypoints per bbox in YOLO keypoint detection.
method
property
nPrototypes
Number of prototypes per bbox in YOLO instance segmnetation.
method
property
postprocessorPath
Path to the postprocessor.
method
property
protosOutputs
Output name for the protos.
method
property
scoresOutputs
Output name corresponding to predicted bounding box confidence scores.
method
property
strides
Strides for each YOLO output.
method
property
subtype
YOLO family decoding subtype (e.g. yolov5, yolov6, yolov7 etc.).
method
property
yoloOutputs
A list of output names for each of the different YOLO grid sizes.
method
class

depthai.nn_archive.v1.MetadataClass

method
property
name
Name of the model.
method
property
path
Relative path to the model executable.
method
property
precision
Precision of the model weights.
method
class

depthai.nn_archive.v1.Output

method
property
dtype
Data type of the output data (e.g., 'float32').
method
property
layout
List of letters describing the output layout (e.g. 'NC').
method
property
name
Name of the output layer.
method
property
shape
Shape of the output as a list of integers (e.g. [1, 1000]).
method
class

depthai.nn_archive.v1.PreprocessingBlock

method
property
daiType
DepthAI input type which is read by DepthAI to automatically setup the pipeline.
method
property
interleavedToPlanar
If True input to the model is interleaved (NHWC) else planar (NCHW).
method
property
mean
Mean values in channel order. Order depends on the order in which the model was trained on.
method
property
reverseChannels
If True input to the model is RGB else BGR.
method
property
scale
Standardization values in channel order. Order depends on the order in which the model was trained on.
method
package

depthai.node

module
class
class
class
ColorCamera
ColorCamera node. For use with color sensors.
class
class
MonoCamera
MonoCamera node. For use with grayscale sensors.
class
StereoDepth
StereoDepth node. Compute stereo disparity and depth from left-right image pair.
class
NeuralNetwork
NeuralNetwork node. Runs a neural inference on input data.
class
VideoEncoder
VideoEncoder node. Encodes frames into MJPEG, H264 or H265.
class
ImageManip
ImageManip node. Capability to crop, resize, warp, ... incoming image frames
class
Warp
Warp node. Capability to crop, resize, warp, ... incoming image frames
class
SPIOut
SPIOut node. Sends messages over SPI.
class
SPIIn
SPIIn node. Receives messages over SPI.
class
DetectionNetwork
DetectionNetwork, base for different network specializations
class
SystemLogger
SystemLogger node. Send system information periodically.
class
class
SpatialLocationCalculator
SpatialLocationCalculator node. Calculates the spatial locations of detected objects based on the input depth map. Spatial location calculations can be additionally refined by using a segmentation mask. If keypoints are provided, the spatial location is calculated around each keypoint.
class
SpatialDetectionNetwork
SpatialDetectionNetwork node. Runs a neural inference on input image and calculates spatial location data.
class
ObjectTracker
ObjectTracker node. Performs object tracking using Kalman filter and hungarian algorithm.
class
IMU
IMU node for BNO08X.
class
EdgeDetector
EdgeDetector node. Performs edge detection using 3x3 Sobel filter
class
FeatureTracker
FeatureTracker node. Performs feature tracking and reidentification using motion estimation between 2 consecutive frames.
class
AprilTag
AprilTag node.
class
DetectionParser
DetectionParser node. Parses detection results from Mobilenet-SSD or YOLO neural networks. @note If multiple detection heads are present in the NNArchive, only one type is supported (either YOLO or Mobilenet-SSD) and the last one will be used.
class
SegmentationParser
SegmentationParser node. Parses raw segmentation output from segmentation neural networks into a dai::SegmentationMask datatype. The parser supports two output model types: 1. Single-channel output where the model argmaxes the class probabilities internally and outputs a single channel mask with class indices. 2. Multi-channel output where each channel corresponds to the probability map for a specific class. The parser will perform argmax across channels to generate the final mask. The parser can be configured to treat the first class (index 0) as the background class, which will be ignored in the final segmentation mask.  .. warning::     Only OAK4 supports running SegmentationParser on device. On other platforms,     the node will automatically switch to host execution.
class
UVC
UVC (USB Video Class) node
class
Thermal
Thermal node.
class
ToFBase
ToFBase node. Performs feature tracking and reidentification using motion estimation between 2 consecutive frames.
class
class
PointCloud
PointCloud node. Computes point cloud from depth frames.
class
Sync
Sync node. Performs syncing between image frames
class
class
class
class
RecordVideo
RecordVideo node, used to record a video source stream to a file
class
RecordMetadataOnly
RecordMetadataOnly node, used to record a source stream to a file
class
class
ToFDepthConfidenceFilter
Node for depth confidence filter, designed to be used with the `ToF` node.
class
ReplayVideo
Replay node, used to replay a file to a source node
class
ReplayMetadataOnly
Replay node, used to replay a file to a source node
class
ImageAlign
ImageAlign node. Calculates spatial location data on a set of ROIs on depth map.
class
Align
Align node. Aligns ImgFrame and Transformable messages using ImgTransformation metadata.
class
RGBD
RGBD node. Combines depth and color frames into a single point cloud.
class
class
NeuralDepth
NeuralDepth node. Compute depth from left-right image pair using neural network.
class
GPUStereo
GPU-accelerated stereo depth node for RVC4.  Computes disparity and depth maps from a synchronized stereo camera pair using OpenCL on the Adreno GPU. Supports both rectified and unrectified inputs (controlled via setRectification).
class
Depth
Depth node. Unified depth output from StereoDepth, NeuralDepth, NeuralAssistedStereo, ToF, or GPUStereo.  With Algorithm::AUTO, the backend is chosen from device capabilities, target FPS, and stereo resolution. On RVC4 this prefers NeuralDepth when available; on other platforms it uses ToF when a ToF sensor is connected, otherwise StereoDepth.  Use build() to pin algorithm, FPS, or resolution before the first depth() / confidence() access. Use setAlignTo() to align depth to another camera output.
class
NeuralAssistedStereo
NeuralAssistedStereo node. Combines Neural Depth with VPP and traditional Stereo Depth.  This composite node internally creates and connects: - Rectification node (full resolution) - NeuralDepth node (low resolution depth estimation) - VPP node (applies virtual projection pattern) - StereoDepth node (final depth computation on VPP-enhanced images)  Pipeline structure: Left/Right Cameras → Rectification → [Full res to VPP] ↓ NeuralDepth (low res) → [disparity + confidence to VPP] ↓ VPP (combines neural depth with full res images) ↓ StereoDepth → Final Depth Output
class
Vpp
Vpp node. Apply Virtual Projection Pattern algorithm to stereo images based on disparity or depth.
class
Gate
Gate Node.  This node acts as a valve for data pipelines. It controls the flow of messages from the 'input' to the 'output' based on the state configured via 'inputControl'. It can be configured to stay open indefinitely, stay closed, or open for a specific number of messages.
class
BasaltVIO
Basalt Visual Inertial Odometry node. Performs VIO on stereo images and IMU data.
class
RTABMapVIO
RTABMap Visual Inertial Odometry node. Performs VIO on rectified frame, depth frame and IMU data.
class
RTABMapSLAM
RTABMap SLAM node. Performs SLAM on given odometry pose, rectified frame and depth frame.
class
class
module

depthai.node.internal

class
XLinkInBridge
XLink bridge structure for host-to-device communication Contains pointers to XLinkOutHost and XLinkIn nodes
class
XLinkOutBridge
XLink bridge structure for device-to-host communication Contains pointers to XLinkOut and XLinkInHost nodes
class
class
class
class
class

depthai.node.internal.XLinkInBridge

property
property
class

depthai.node.internal.XLinkOutBridge

property
property
class

depthai.node.internal.XLinkIn(depthai.DeviceNode)

method
getMaxDataSize(self) -> int: int
Get maximum messages size in bytes
method
getNumFrames(self) -> int: int
Get number of frames in pool
method
method
setMaxDataSize(self, maxDataSize: int)
Set maximum message size it can receive  Parameter ``maxDataSize``:     Maximum size in bytes
method
setNumFrames(self, numFrames: int)
Set number of frames in pool for sending messages forward  Parameter ``numFrames``:     Maximum number of frames in pool
method
setStreamName(self, name: str)
Specifies XLink stream name to use.  The name should not start with double underscores '__', as those are reserved for internal use.  Parameter ``name``:     Stream name
property
class

depthai.node.internal.XLinkOut(depthai.DeviceNode)

method
method
getFpsLimit(self) -> float: float
Get rate limit in messages per second
method
getMetadataOnly(self) -> bool: bool
Get whether to transfer only messages attributes and not buffer data
method
method
method
method
setFpsLimit(self, fps: float)
Specifies a message sending limit. It's approximated from specified rate.  Parameter ``fps``:     Approximate rate limit in messages per second
method
setMetadataOnly(self, metadataOnly: bool)
Specify whether to transfer only messages attributes and not buffer data
method
method
setStreamName(self, name: str)
Specifies XLink stream name to use.  The name should not start with double underscores '__', as those are reserved for internal use.  Parameter ``name``:     Stream name
property
class

depthai.node.internal.XLinkInHost(depthai.Node)

class

depthai.node.internal.XLinkOutHost(depthai.Node)

class

depthai.node.BenchmarkOut(depthai.DeviceNode)

method
setFps(self, fps: float)
Set FPS at which the node is sending out messages. 0 means as fast as possible
method
setNumMessagesToSend(self, num: int)
Sets number of messages to send, by default send messages indefinitely  Parameter ``num``:     number of messages to send
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on device.
property
input
Message that will be sent repeatedly
property
out
Send messages out as fast as possible
class

depthai.node.BenchmarkIn(depthai.DeviceNode)

method
method
method
sendReportEveryNMessages(self, num: int)
Specify how many messages to measure for each report
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on device.
property
input
Receive messages as fast as possible
property
passthrough
Passthrough for input messages (so the node can be placed between other nodes)
property
report
Send a benchmark report when the set number of messages are received
class

depthai.node.ColorCamera(depthai.DeviceNode)

method
method
getBoardSocket(self) -> depthai.CameraBoardSocket: depthai.CameraBoardSocket
Retrieves which board socket to use  Returns:     Board socket to use
method
method
getCamera(self) -> str: str
Retrieves which camera to use by name  Returns:     Name of the camera to use
method
method
getFp16(self) -> bool: bool
Get fp16 (0..255) data of preview output frames
method
getFps(self) -> float: float
Get rate at which camera should produce frames  Returns:     Rate in frames per second
method
method
method
getInterleaved(self) -> bool: bool
Get planar or interleaved data of preview output frames
method
getIspHeight(self) -> int: int
Get 'isp' output height
method
getIspNumFramesPool(self) -> int: int
Get number of frames in isp pool
method
getIspSize(self) -> tuple[int, int]: tuple[int, int]
Get 'isp' output resolution as size, after scaling
method
getIspWidth(self) -> int: int
Get 'isp' output width
method
method
getPreviewKeepAspectRatio(self) -> bool: bool
See also:     setPreviewKeepAspectRatio  Returns:     Preview keep aspect ratio option
method
getPreviewNumFramesPool(self) -> int: int
Get number of frames in preview pool
method
method
method
getRawNumFramesPool(self) -> int: int
Get number of frames in raw pool
method
method
getResolutionHeight(self) -> int: int
Get sensor resolution height
method
method
getResolutionWidth(self) -> int: int
Get sensor resolution width
method
method
getSensorCropX(self) -> float: float
Get sensor top left x crop coordinate
method
getSensorCropY(self) -> float: float
Get sensor top left y crop coordinate
method
method
getStillNumFramesPool(self) -> int: int
Get number of frames in still pool
method
method
method
method
getVideoNumFramesPool(self) -> int: int
Get number of frames in video pool
method
method
method
sensorCenterCrop(self)
Specify sensor center crop. Resolution size / video size
method
setBoardSocket(self, boardSocket: depthai.CameraBoardSocket)
Specify which board socket to use  Parameter ``boardSocket``:     Board socket to use
method
method
setCamera(self, name: str)
Specify which camera to use by name  Parameter ``name``:     Name of the camera to use
method
setColorOrder(self, colorOrder: depthai.ColorCameraProperties.ColorOrder)
Set color order of preview output images. RGB or BGR
method
setFp16(self, fp16: bool)
Set fp16 (0..255) data type of preview output frames
method
setFps(self, fps: float)
Set rate at which camera should produce frames  Parameter ``fps``:     Rate in frames per second
method
method
method
setInterleaved(self, interleaved: bool)
Set planar or interleaved data of preview output frames
method
setIsp3aFps(self, arg0: int)
Isp 3A rate (auto focus, auto exposure, auto white balance, camera controls etc.). Default (0) matches the camera FPS, meaning that 3A is running on each frame. Reducing the rate of 3A reduces the CPU usage on CSS, but also increases the convergence rate of 3A. Note that camera controls will be processed at this rate. E.g. if camera is running at 30 fps, and camera control is sent at every frame, but 3A fps is set to 15, the camera control messages will be processed at 15 fps rate, which will lead to queueing.
method
setIspNumFramesPool(self, arg0: int)
Set number of frames in isp pool
method
method
method
setPreviewKeepAspectRatio(self, keep: bool)
Specifies whether preview output should preserve aspect ratio, after downscaling from video size or not.  Parameter ``keep``:     If true, a larger crop region will be considered to still be able to create     the final image in the specified aspect ratio. Otherwise video size is     resized to fit preview size
method
setPreviewNumFramesPool(self, arg0: int)
Set number of frames in preview pool
method
method
setRawNumFramesPool(self, arg0: int)
Set number of frames in raw pool
method
setRawOutputPacked(self, packed: bool)
Configures whether the camera `raw` frames are saved as MIPI-packed to memory. The packed format is more efficient, consuming less memory on device, and less data to send to host: RAW10: 4 pixels saved on 5 bytes, RAW12: 2 pixels saved on 3 bytes. When packing is disabled (`false`), data is saved lsb-aligned, e.g. a RAW10 pixel will be stored as uint16, on bits 9..0: 0b0000'00pp'pppp'pppp. Default is auto: enabled for standard color/monochrome cameras where ISP can work with both packed/unpacked, but disabled for other cameras like ToF.
method
method
setSensorCrop(self, x: float, y: float)
Specifies the cropping that happens when converting ISP to video output. By default, video will be center cropped from the ISP output. Note that this doesn't actually do on-sensor cropping (and MIPI-stream only that region), but it does postprocessing on the ISP (on RVC).  Parameter ``x``:     Top left X coordinate  Parameter ``y``:     Top left Y coordinate
method
setStillNumFramesPool(self, arg0: int)
Set number of frames in preview pool
method
method
setVideoNumFramesPool(self, arg0: int)
Set number of frames in preview pool
method
property
frameEvent
Outputs metadata-only ImgFrame message as an early indicator of an incoming frame.  It's sent on the MIPI SoF (start-of-frame) event, just after the exposure of the current frame has finished and before the exposure for next frame starts. Could be used to synchronize various processes with camera capture. Fields populated: camera id, sequence number, timestamp
property
initialControl
Initial control options to apply to sensor
property
inputControl
Input for CameraControl message, which can modify camera parameters in runtime
property
isp
Outputs ImgFrame message that carries YUV420 planar (I420/IYUV) frame data.  Generated by the ISP engine, and the source for the 'video', 'preview' and 'still' outputs
property
preview
Outputs ImgFrame message that carries BGR/RGB planar/interleaved encoded frame data.  Suitable for use with NeuralNetwork node
property
raw
Outputs ImgFrame message that carries RAW10-packed (MIPI CSI-2 format) frame data.  Captured directly from the camera sensor, and the source for the 'isp' output.
property
still
Outputs ImgFrame message that carries NV12 encoded (YUV420, UV plane interleaved) frame data.  The message is sent only when a CameraControl message arrives to inputControl with captureStill command set.
property
video
Outputs ImgFrame message that carries NV12 encoded (YUV420, UV plane interleaved) frame data.  Suitable for use with VideoEncoder node
class

depthai.node.Camera(depthai.DeviceNode)

method
method
getBoardSocket(self) -> depthai.CameraBoardSocket: depthai.CameraBoardSocket
Retrieves which board socket to use  Returns:     Board socket to use
method
method
getIspNumFramesPool(self) -> int: int
Get number of frames in isp pool  Returns:     Number of frames
method
getMaxSizePoolIsp(self) -> int: int
Get maximum size of isp pool  Returns:     Maximum size in bytes of isp pool
method
getMaxSizePoolRaw(self) -> int: int
Get maximum size of raw pool  Returns:     Maximum size in bytes of raw pool
method
getOutputsMaxSizePool(self) -> int|None: int|None
Get maximum size of outputs pool for all outputs  Returns:     Maximum size in bytes of image manip pool
method
getOutputsNumFramesPool(self) -> int|None: int|None
Get number of frames in outputs pool for all outputs  Returns:     Number of frames
method
getRawNumFramesPool(self) -> int: int
Get number of frames in raw pool  Returns:     Number of frames
method
method
requestFullResolutionOutput(self, type: depthai.ImgFrame.Type|None = None, fps: float|None = None, useHighestResolution: bool = False) -> depthai.Node.Output: depthai.Node.Output
Get a high resolution output with full FOV on the sensor. By default the function will not use the resolutions higher than 5000x4000, as those often need a lot of resources, making them hard to use in combination with other nodes.  Parameter ``type``:     Type of the output (NV12, BGR, ...) - by default it's auto-selected for best     performance  Parameter ``fps``:     FPS of the output - by default it's auto-selected to highest possible that a     sensor config support or 30, whichever is lower  Parameter ``useHighestResolution``:     If true, the function will use the highest resolution available on the     sensor, even if it's higher than 5000x4000
method
method
method
setImageOrientation(self, imageOrientation: depthai.CameraImageOrientation) -> Camera: Camera
Set camera image orientation  Parameter ``imageOrientation``:     Image orientation to set  Returns:     Shared pointer to the camera node
method
setIspNumFramesPool(self, num: int) -> Camera: Camera
Set number of frames in isp pool (will be automatically reduced if the maximum pool memory size is exceeded)  Parameter ``num``:     Number of frames  Returns:     Shared pointer to the camera node
method
setMaxSizePoolIsp(self, size: int) -> Camera: Camera
Set maximum size of isp pool  Parameter ``size``:     Maximum size in bytes of isp pool  Returns:     Shared pointer to the camera node
method
setMaxSizePoolRaw(self, size: int) -> Camera: Camera
Set maximum size of raw pool  Parameter ``size``:     Maximum size in bytes of raw pool  Returns:     Shared pointer to the camera node
method
setMaxSizePools(self, raw: int, isp: int, imgmanip: int) -> Camera: Camera
Set maximum memory size of all pools  Parameter ``raw``:     Maximum size in bytes of raw pool  Parameter ``isp``:     Maximum size in bytes of isp pool  Parameter ``outputs``:     Maximum size in bytes of outputs pools  Returns:     Shared pointer to the camera node
method
setMockIsp(self, mockIsp: ReplayVideo) -> Camera: Camera
Set mock ISP for Camera node. Automatically sets mockIsp size.  Parameter ``replay``:     ReplayVideo node to use as mock ISP
method
setNumFramesPools(self, raw: int, isp: int, imgmanip: int) -> Camera: Camera
Set number of frames in all pools (will be automatically reduced if the maximum pool memory size is exceeded)  Parameter ``raw``:     Number of frames in raw pool  Parameter ``isp``:     Number of frames in isp pool  Parameter ``outputs``:     Number of frames in outputs pools  Returns:     Shared pointer to the camera node
method
setOutputsMaxSizePool(self, size: int) -> Camera: Camera
Set maximum size of pools for all outputs  Parameter ``size``:     Maximum size in bytes of pools for all outputs  Returns:     Shared pointer to the camera node
method
setOutputsNumFramesPool(self, num: int) -> Camera: Camera
Set number of frames in pools for all outputs  Parameter ``num``:     Number of frames in pools for all outputs  Returns:     Shared pointer to the camera node
method
setRawNumFramesPool(self, num: int) -> Camera: Camera
Set number of frames in raw pool (will be automatically reduced if the maximum pool memory size is exceeded)  Parameter ``num``:     Number of frames  Returns:     Shared pointer to the camera node
method
setSensorType(self, sensorType: depthai.CameraSensorType) -> Camera: Camera
Set the sensor type to use  Parameter ``sensorType``:     Sensor type to use
property
initialControl
Initial control options to apply to sensor
property
inputControl
Input for CameraControl message, which can modify camera parameters in runtime
property
mockIsp
Input for mocking 'isp' functionality on RVC2. Default queue is blocking with size 8
property
raw
Outputs ImgFrame message that carries RAW10-packed (MIPI CSI-2 format) frame data.  Captured directly from the camera sensor, and the source for the 'isp' output.
class

depthai.node.MonoCamera(depthai.DeviceNode)

method
getBoardSocket(self) -> depthai.CameraBoardSocket: depthai.CameraBoardSocket
Retrieves which board socket to use  Returns:     Board socket to use
method
method
getCamera(self) -> str: str
Retrieves which camera to use by name  Returns:     Name of the camera to use
method
getFps(self) -> float: float
Get rate at which camera should produce frames  Returns:     Rate in frames per second
method
method
method
getNumFramesPool(self) -> int: int
Get number of frames in main (ISP output) pool
method
getRawNumFramesPool(self) -> int: int
Get number of frames in raw pool
method
method
getResolutionHeight(self) -> int: int
Get sensor resolution height
method
method
getResolutionWidth(self) -> int: int
Get sensor resolution width
method
setBoardSocket(self, boardSocket: depthai.CameraBoardSocket)
Specify which board socket to use  Parameter ``boardSocket``:     Board socket to use
method
method
setCamera(self, name: str)
Specify which camera to use by name  Parameter ``name``:     Name of the camera to use
method
setFps(self, fps: float)
Set rate at which camera should produce frames  Parameter ``fps``:     Rate in frames per second
method
method
method
setIsp3aFps(self, arg0: int)
Isp 3A rate (auto focus, auto exposure, auto white balance, camera controls etc.). Default (0) matches the camera FPS, meaning that 3A is running on each frame. Reducing the rate of 3A reduces the CPU usage on CSS, but also increases the convergence rate of 3A. Note that camera controls will be processed at this rate. E.g. if camera is running at 30 fps, and camera control is sent at every frame, but 3A fps is set to 15, the camera control messages will be processed at 15 fps rate, which will lead to queueing.
method
setNumFramesPool(self, arg0: int)
Set number of frames in main (ISP output) pool
method
setRawNumFramesPool(self, arg0: int)
Set number of frames in raw pool
method
setRawOutputPacked(self, packed: bool)
Configures whether the camera `raw` frames are saved as MIPI-packed to memory. The packed format is more efficient, consuming less memory on device, and less data to send to host: RAW10: 4 pixels saved on 5 bytes, RAW12: 2 pixels saved on 3 bytes. When packing is disabled (`false`), data is saved lsb-aligned, e.g. a RAW10 pixel will be stored as uint16, on bits 9..0: 0b0000'00pp'pppp'pppp. Default is auto: enabled for standard color/monochrome cameras where ISP can work with both packed/unpacked, but disabled for other cameras like ToF.
method
property
property
initialControl
Initial control options to apply to sensor
property
property
property
class

depthai.node.StereoDepth(depthai.DeviceNode)

class
PresetMode
Preset modes for stereo depth.  Members:    FAST_ACCURACY    FAST_DENSITY    DEFAULT    FACE    HIGH_DETAIL    ROBOTICS    DENSITY    ACCURACY
method
method
method
enableDistortionCorrection(self, arg0: bool)
Equivalent to useHomographyRectification(!enableDistortionCorrection)
method
loadMeshData()
Specify mesh calibration data for 'left' and 'right' inputs, as vectors of bytes. Overrides useHomographyRectification behavior. See `loadMeshFiles` for the expected data format
method
loadMeshFiles(self, pathLeft: os.PathLike, pathRight: os.PathLike)
Specify local filesystem paths to the mesh calibration files for 'left' and 'right' inputs.  When a mesh calibration is set, it overrides the camera intrinsics/extrinsics matrices. Overrides useHomographyRectification behavior. Mesh format: a sequence of (y,x) points as 'float' with coordinates from the input image to be mapped in the output. The mesh can be subsampled, configured by `setMeshStep`.  With a 1280x800 resolution and the default (16,16) step, the required mesh size is:  width: 1280 / 16 + 1 = 81  height: 800 / 16 + 1 = 51
method
setAlphaScaling(self, arg0: float)
Free scaling parameter between 0 (when all the pixels in the undistorted image are valid) and 1 (when all the source image pixels are retained in the undistorted image). On some high distortion lenses, and/or due to rectification (image rotated) invalid areas may appear even with alpha=0, in these cases alpha < 0.0 helps removing invalid areas. See getOptimalNewCameraMatrix from opencv for more details.
method
setBaseline(self, arg0: float)
Override baseline from calibration. Used only in disparity to depth conversion. Units are centimeters.
method
setDefaultProfilePreset(self, arg0: StereoDepth.PresetMode)
Sets a default preset based on specified option.  Parameter ``mode``:     Stereo depth preset mode  .. warning::     If using alpha scaling on RVC4 the DEFAULT, DENSITY, and FAST_DENSITY     presets can produce inaccurate depth in black padded regions, as they     prioritize coverage.
method
method
setDepthAlignmentUseSpecTranslation(self, arg0: bool)
Use baseline information for depth alignment from specs (design data) or from calibration. Default: true
method
setDisparityToDepthUseSpecTranslation(self, arg0: bool)
Use baseline information for disparity to depth conversion from specs (design data) or from calibration. Default: true
method
setExtendedDisparity(self, enable: bool)
Disparity range increased from 0-95 to 0-190, combined from full resolution and downscaled images.  Suitable for short range objects. Currently incompatible with sub-pixel disparity
method
setFocalLength(self, arg0: float)
Override focal length from calibration. Used only in disparity to depth conversion. Units are pixels.
method
method
setLeftRightCheck(self, enable: bool)
Computes and combines disparities in both L-R and R-L directions, and combine them.  For better occlusion handling, discarding invalid disparity values
method
setMeshStep(self, width: int, height: int)
Set the distance between mesh points. Default: (16, 16)
method
setNumFramesPool(self, arg0: int)
Specify number of frames in pool.  Parameter ``numFramesPool``:     How many frames should the pool have
method
setOutputKeepAspectRatio(self, keep: bool)
Specifies whether the frames resized by `setOutputSize` should preserve aspect ratio, with potential cropping when enabled. Default `true`
method
setOutputSize(self, width: int, height: int)
Specify disparity/depth output resolution size, implemented by scaling.  Currently only applicable when aligning to RGB camera
method
setPostProcessingHardwareResources(self, arg0: int, arg1: int)
Specify allocated hardware resources for stereo depth. Suitable only to increase post processing runtime.  Parameter ``numShaves``:     Number of shaves.  Parameter ``numMemorySlices``:     Number of memory slices.
method
setRectification(self, enable: bool)
Rectify input images or not.
method
setRectificationUseSpecTranslation(self, arg0: bool)
Obtain rectification matrices using spec translation (design data) or from calibration in calculations. Should be used only for debugging. Default: false
method
setRectifyEdgeFillColor(self, color: int)
Fill color for missing data at frame edges  Parameter ``color``:     Grayscale 0..255, or -1 to replicate pixels
method
setRuntimeModeSwitch(self, arg0: bool)
Enable runtime stereo mode switch, e.g. from standard to LR-check. Note: when enabled resources allocated for worst case to enable switching to any mode.
method
setSubpixel(self, enable: bool)
Computes disparity with sub-pixel interpolation (3 fractional bits by default).  Suitable for long range. Currently incompatible with extended disparity
method
setSubpixelFractionalBits(self, subpixelFractionalBits: int)
Number of fractional bits for subpixel mode. Default value: 3. Valid values: 3,4,5. Defines the number of fractional disparities: 2^x. Median filter postprocessing is supported only for 3 fractional bits.
method
useHomographyRectification(self, arg0: bool)
Use 3x3 homography matrix for stereo rectification instead of sparse mesh generated on device. Default behaviour is AUTO, for lenses with FOV over 85 degrees sparse mesh is used, otherwise 3x3 homography. If custom mesh data is provided through loadMeshData or loadMeshFiles this option is ignored.  Parameter ``useHomographyRectification``:     true: 3x3 homography matrix generated from calibration data is used for     stereo rectification, can't correct lens distortion. false: sparse mesh is     generated on-device from calibration data with mesh step specified with     setMeshStep (Default: (16, 16)), can correct lens distortion. Implementation     for generating the mesh is same as opencv's initUndistortRectifyMap     function. Only the first 8 distortion coefficients are used from calibration     data.
property
confidenceMap
Outputs ImgFrame message that carries RAW8 confidence map. Lower values mean lower confidence of the calculated disparity value. RGB alignment, left-right check or any postprocessing (e.g., median filter) is not performed on confidence map.
property
debugDispCostDump
Outputs ImgFrame message that carries cost dump of disparity map. Useful for debugging/fine tuning.
property
debugDispLrCheckIt1
Outputs ImgFrame message that carries left-right check first iteration (before combining with second iteration) disparity map. Useful for debugging/fine tuning.
property
debugDispLrCheckIt2
Outputs ImgFrame message that carries left-right check second iteration (before combining with first iteration) disparity map. Useful for debugging/fine tuning.
property
debugExtDispLrCheckIt1
Outputs ImgFrame message that carries extended left-right check first iteration (downscaled frame, before combining with second iteration) disparity map. Useful for debugging/fine tuning.
property
debugExtDispLrCheckIt2
Outputs ImgFrame message that carries extended left-right check second iteration (downscaled frame, before combining with first iteration) disparity map. Useful for debugging/fine tuning.
property
depth
Outputs ImgFrame message that carries RAW16 encoded (0..65535) depth data in depth units (millimeter by default).  Non-determined / invalid depth values are set to 0
property
disparity
Outputs ImgFrame message that carries RAW8 / RAW16 encoded disparity data: RAW8 encoded (0..95) for standard mode; RAW8 encoded (0..190) for extended disparity mode; RAW16 encoded for subpixel disparity mode: - 0..760 for 3 fractional bits (by default) - 0..1520 for 4 fractional bits - 0..3040 for 5 fractional bits
property
initialConfig
Initial config to use for StereoDepth.
property
inputAlignTo
Input align to message. Default queue is non-blocking with size 1.
property
inputConfig
Input StereoDepthConfig message with ability to modify parameters in runtime.
property
left
Input for left ImgFrame of left-right pair
property
outConfig
Outputs StereoDepthConfig message that contains current stereo configuration.
property
rectifiedLeft
Outputs ImgFrame message that carries RAW8 encoded (grayscale) rectified frame data.
property
rectifiedRight
Outputs ImgFrame message that carries RAW8 encoded (grayscale) rectified frame data.
property
right
Input for right ImgFrame of left-right pair
property
syncedLeft
Passthrough ImgFrame message from 'left' Input.
property
syncedRight
Passthrough ImgFrame message from 'right' Input.
class

depthai.node.NeuralNetwork(depthai.DeviceNode)

class
method
method
getNNArchive(self) -> depthai.NNArchive|None: depthai.NNArchive|None
Get the archive owned by this Node.  Returns:     constant reference to this Nodes archive
method
getNumInferenceThreads(self) -> int: int
How many inference threads will be used to run the network  Returns:     Number of threads, 0, 1 or 2. Zero means AUTO
method
setBackend(self, setBackend: str)
Specifies backend to use  Parameter ``backend``:     String specifying backend to use
method
setBackendProperties(self, setBackendProperties: dict[str, str])
Set backend properties  Parameter ``backendProperties``:     backend properties map
method
method
setBlobPath(self, path: os.PathLike)
Load network blob into assets and use once pipeline is started.  Throws:     Error if file doesn't exist or isn't a valid network blob.  Parameter ``path``:     Path to network blob
method
setFromModelZoo(self, description: depthai.NNModelDescription, useCached: bool)
Download model from zoo and set it for this Node  Parameter ``description:``:     Model description to download  Parameter ``useCached:``:     Use cached model if available
method
setModelFromDeviceZoo(self, model: depthai.DeviceModelZoo)
Set model from Device Model Zoo  Parameter ``model``:     DeviceModelZoo model enum @note Only applicable for RVC4 devices with OS     1.20.5 or higher
method
setModelPath(self, modelPath: os.PathLike)
Load a network model into assets. DLC and other custom model files are loaded lazily and must remain available and unchanged until the pipeline has been built.  Parameter ``modelPath``:     Path to the neural network model file.
method
method
setNumInferenceThreads(self, numThreads: int)
How many threads should the node use to run the network.  Parameter ``numThreads``:     Number of threads to dedicate to this node
method
setNumNCEPerInferenceThread(self, numNCEPerThread: int)
How many Neural Compute Engines should a single thread use for inference  Parameter ``numNCEPerThread``:     Number of NCE per thread
method
setNumPoolFrames(self, numFrames: int)
Specifies how many frames will be available in the pool  Parameter ``numFrames``:     How many frames will pool have
method
setNumShavesPerInferenceThread(self, numShavesPerInferenceThread: int)
How many Shaves should a single thread use for inference  Parameter ``numShavesPerThread``:     Number of shaves per thread
method
property
input
Input message with data to be inferred upon
property
inputs
Inputs mapped to network inputs. Useful for inferring from separate data sources Default input is non-blocking with queue size 1 and waits for messages
property
out
Outputs NNData message that carries inference results
property
passthrough
Passthrough message on which the inference was performed.  Suitable for when input queue is set to non-blocking behavior.
property
passthroughs
Passthroughs which correspond to specified input
class

depthai.node.VideoEncoder(depthai.DeviceNode)

method
method
method
method
method
method
method
getLossless(self) -> bool: bool
Get lossless mode. Applies only when using [M]JPEG profile.
method
method
getNumBFrames(self) -> int: int
Get number of B frames
method
getNumFramesPool(self) -> int: int
Get number of frames in pool  Returns:     Number of pool frames
method
method
method
method
setBitrate(self, bitrate: int)
Set output bitrate in bps, for CBR rate control mode. 0 for auto (based on frame size and FPS)
method
setBitrateKbps(self, bitrateKbps: int)
Set output bitrate in kbps, for CBR rate control mode. 0 for auto (based on frame size and FPS)
method
setDefaultProfilePreset(self, fps: float, profile: depthai.VideoEncoderProperties.Profile)
Sets a default preset based on specified frame rate and profile  Parameter ``fps``:     Frame rate in frames per second  Parameter ``profile``:     Encoding profile
method
setFrameRate(self, frameRate: float)
Sets expected frame rate  Parameter ``frameRate``:     Frame rate in frames per second
method
setKeyframeFrequency(self, freq: int)
Set keyframe frequency. Every Nth frame a keyframe is inserted.  Applicable only to H264 and H265 profiles  Examples:  - 30 FPS video, keyframe frequency: 30. Every 1s a keyframe will be inserted  - 60 FPS video, keyframe frequency: 180. Every 3s a keyframe will be inserted
method
setLossless(self, arg0: bool)
Set lossless mode. Applies only to [M]JPEG profile  Parameter ``lossless``:     True to enable lossless jpeg encoding, false otherwise
method
setMaxOutputFrameSize(self, maxFrameSize: int)
Specifies maximum output encoded frame size
method
setNumBFrames(self, numBFrames: int)
Set number of B frames to be inserted
method
setNumFramesPool(self, frames: int)
Set number of frames in pool  Parameter ``frames``:     Number of pool frames
method
method
setQuality(self, quality: int)
Set quality  Parameter ``quality``:     Value between 0-100%. Approximates quality
method
property
bitstream
Outputs ImgFrame message that carries BITSTREAM encoded (MJPEG, H264 or H265) frame data. Mutually exclusive with out.
property
input
Input for NV12 ImgFrame to be encoded
property
out
Outputs EncodedFrame message that carries encoded (MJPEG, H264 or H265) frame data. Mutually exclusive with bitstream.
class

depthai.node.ImageManip(depthai.DeviceNode)

class
PerformanceMode
Members:    BALANCED    PERFORMANCE    LOW_POWER
class
Backend
Members:    HW    CPU    GPU    AUTO
method
setBackend(self, arg0: depthai.ImageManipProperties.Backend) -> ImageManip: ImageManip
Set backend preference: - CPU: Run ImageManip on the CPU. - HW: Prefer the dedicated hardware image manipulation backend. - GPU: Prefer the GPU backend. - AUTO: Let the runtime select the backend automatically (GPU with CPU fallback).  Hardware-accelerated backends can cause some unexpected behavior when using multiple ImageManip nodes in series. Currently, the only operation affected is downscaling.  Parameter ``backend``:     Backend preference
method
setMaxOutputFrameSize(self, arg0: int)
Specify maximum size of output image.  Parameter ``maxFrameSize``:     Maximum frame size in bytes
method
setMaxPoolSize(self, arg0: int)
Specify maximum size of output image pool.  Parameter ``maxPoolSize``:     Maximum pool size in bytes
method
setNumFramesPool(self, arg0: int)
Specify number of frames in pool.  Parameter ``numFramesPool``:     How many frames should the pool have
method
setPerformanceMode(self, arg0: depthai.ImageManipProperties.PerformanceMode) -> ImageManip: ImageManip
Set performance mode  Parameter ``performanceMode``:     Performance mode
method
setRunOnHost(self, arg0: bool) -> ImageManip: ImageManip
Specify whether to run on host or device  Parameter ``runOnHost``:     Run node on host
property
initialConfig
Initial config to use when manipulating frames
property
inputConfig
Input ImageManipConfig message with ability to modify parameters in runtime
property
inputImage
Input image to be modified
property
class

depthai.node.Warp(depthai.DeviceNode)

method
getHwIds(self) -> list[int]: list[int]
Retrieve which hardware warp engines to use
method
method
setHwIds(self, arg0: list[int])
Specify which hardware warp engines to use  Parameter ``ids``:     Which warp engines to use (0, 1, 2)
method
setInterpolation(self, arg0: depthai.Interpolation)
Specify which interpolation method to use  Parameter ``interpolation``:     type of interpolation
method
setMaxOutputFrameSize(self, arg0: int)
Specify maximum size of output image.  Parameter ``maxFrameSize``:     Maximum frame size in bytes
method
setNumFramesPool(self, arg0: int)
Specify number of frames in pool.  Parameter ``numFramesPool``:     How many frames should the pool have
method
method
property
inputImage
Input image to be modified Default queue is blocking with size 8
property
out
Outputs ImgFrame message that carries warped image.
class

depthai.node.SPIOut(depthai.DeviceNode)

method
setBusId(self, id: int)
Specifies SPI Bus number to use  Parameter ``id``:     SPI Bus id
method
setStreamName(self, name: str)
Specifies stream name over which the node will send data  Parameter ``name``:     Stream name
property
input
Input for any type of messages to be transferred over SPI stream Default queue is blocking with size 8
class

depthai.node.SPIIn(depthai.DeviceNode)

method
method
getMaxDataSize(self) -> int: int
Get maximum messages size in bytes
method
getNumFrames(self) -> int: int
Get number of frames in pool
method
method
setBusId(self, id: int)
Specifies SPI Bus number to use  Parameter ``id``:     SPI Bus id
method
setMaxDataSize(self, maxDataSize: int)
Set maximum message size it can receive  Parameter ``maxDataSize``:     Maximum size in bytes
method
setNumFrames(self, numFrames: int)
Set number of frames in pool for sending messages forward  Parameter ``numFrames``:     Maximum number of frames in pool
method
setStreamName(self, name: str)
Specifies stream name over which the node will receive data  Parameter ``name``:     Stream name
property
out
Outputs message of same type as send from host.
class

depthai.node.DetectionNetwork(depthai.DeviceNodeGroup)

class
method
method
method
method
getConfidenceThreshold(self) -> float: float
Retrieves threshold at which to filter the rest of the detections.  Returns:     Detection confidence
method
getNumInferenceThreads(self) -> int: int
How many inference threads will be used to run the network  Returns:     Number of threads, 0, 1 or 2. Zero means AUTO
method
setBackend(self, setBackend: str)
Specifies backend to use  Parameter ``backend``:     String specifying backend to use
method
setBackendProperties(self, setBackendProperties: dict[str, str])
Set backend properties  Parameter ``backendProperties``:     backend properties map
method
method
setBlobPath(self, path: os.PathLike)
Load network blob into assets and use once pipeline is started.  Throws:     Error if file doesn't exist or isn't a valid network blob.  Parameter ``path``:     Path to network blob
method
setConfidenceThreshold(self, thresh: float)
Specifies confidence threshold at which to filter the rest of the detections.  Parameter ``thresh``:     Detection confidence must be greater than specified threshold to be added to     the list
method
setFromModelZoo(self, description: depthai.NNModelDescription, useCached: bool = False)
Download model from zoo and set it for this Node  Parameter ``description:``:     Model description to download  Parameter ``useCached:``:     Use cached model if available
method
setModelPath(self, modelPath: os.PathLike)
Load a network model into assets. DLC and other custom model files are loaded lazily and must remain available and unchanged until the pipeline has been built.  Parameter ``modelPath``:     Path to the model file.
method
method
setNumInferenceThreads(self, numThreads: int)
How many threads should the node use to run the network.  Parameter ``numThreads``:     Number of threads to dedicate to this node
method
setNumNCEPerInferenceThread(self, numNCEPerThread: int)
How many Neural Compute Engines should a single thread use for inference  Parameter ``numNCEPerThread``:     Number of NCE per thread
method
setNumPoolFrames(self, numFrames: int)
Specifies how many frames will be available in the pool  Parameter ``numFrames``:     How many frames will pool have
method
setNumShavesPerInferenceThread(self, numShavesPerInferenceThread: int)
How many Shaves should a single thread use for inference  Parameter ``numShavesPerThread``:     Number of shaves per thread
property
property
input
Input message with data to be inferred upon
property
property
out
Outputs ImgDetections message that carries parsed detection results. Overrides NeuralNetwork 'out' with ImgDetections output message type.
property
outNetwork
Outputs unparsed inference results.
property
passthrough
Passthrough message on which the inference was performed.  Suitable for when input queue is set to non-blocking behavior.
class

depthai.node.SystemLogger(depthai.DeviceNode)

method
getRate(self) -> float: float
Gets logging rate, at which messages will be sent out
method
setRate(self, hz: float)
Specify logging rate, at which messages will be sent out  Parameter ``hz``:     Sending rate in hertz (messages per second)
property
out
Outputs SystemInformation[RVC4] message that carries various system information like memory and CPU usage, temperatures, ... For series 2 devices output SystemInformation message, for series 4 devices output SystemInformationRVC4 message
class

depthai.node.Script(depthai.DeviceNode)

method
getProcessor(self) -> depthai.ProcessorType: depthai.ProcessorType
Get on which processor the script should run  Returns:     Processor type - Leon CSS or Leon MSS
method
getScriptName(self) -> str: str
Get the script name in utf-8.  When name set with setScript() or setScriptPath(), returns that name. When script loaded with setScriptPath() with name not provided, returns the utf-8 string of that path. Otherwise, returns "<script>"  Returns:     std::string of script name in utf-8
method
setProcessor(self, arg0: depthai.ProcessorType)
Set on which processor the script should run  Parameter ``type``:     Processor type - Leon CSS or Leon MSS
method
method
property
property
class

depthai.node.SpatialLocationCalculator(depthai.DeviceNode)

method
runOnHost(self) -> bool: bool
Check if the node is set to run on host
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on device.
property
initialConfig
Initial config to use when calculating spatial location data.
property
inputConfig
Input SpatialLocationCalculatorConfig message with ability to modify parameters in runtime. Default queue is non-blocking with size 4.
property
inputDepth
Input message with depth data used to retrieve spatial information about detected object. Default queue is non-blocking with size 4.
property
inputDetections
Input messages on which spatial location will be calculated. Possible datatypes are ImgDetections or Keypoints.
property
out
Outputs SpatialLocationCalculatorData message that carries spatial locations for each additional ROI that is specified in the config.
property
outputDetections
Outputs SpatialImgDetections message that carries spatial locations along with original input data.
property
passthroughDepth
Passthrough message on which the calculation was performed. Suitable for when input queue is set to non-blocking behavior.
class

depthai.node.SpatialDetectionNetwork(depthai.DeviceNode)

class
method
method
method
getConfidenceThreshold(self) -> float: float
Retrieves threshold at which to filter the rest of the detections.  Returns:     Detection confidence
method
getNumInferenceThreads(self) -> int: int
How many inference threads will be used to run the network  Returns:     Number of threads, 0, 1 or 2. Zero means AUTO
method
setBackend(self, setBackend: str)
Specifies backend to use  Parameter ``backend``:     String specifying backend to use
method
setBackendProperties(self, setBackendProperties: dict[str, str])
Set backend properties  Parameter ``backendProperties``:     backend properties map
method
method
setBlobPath(self, path: os.PathLike)
Load network blob into assets and use once pipeline is started.  Throws:     Error if file doesn't exist or isn't a valid network blob.  Parameter ``path``:     Path to network blob
method
setBoundingBoxScaleFactor(self, scaleFactor: float)
Custom interface  Specifies scale factor for detected bounding boxes.  Parameter ``scaleFactor``:     Scale factor must be in the interval (0,1].
method
setConfidenceThreshold(self, thresh: float)
Specifies confidence threshold at which to filter the rest of the detections.  Parameter ``thresh``:     Detection confidence must be greater than specified threshold to be added to     the list
method
setDepthLowerThreshold(self, lowerThreshold: int)
Specifies lower threshold in depth units (millimeter by default) for depth values which will used to calculate spatial data  Parameter ``lowerThreshold``:     LowerThreshold must be in the interval [0,upperThreshold] and less than     upperThreshold.
method
setDepthUpperThreshold(self, upperThreshold: int)
Specifies upper threshold in depth units (millimeter by default) for depth values which will used to calculate spatial data  Parameter ``upperThreshold``:     UpperThreshold must be in the interval (lowerThreshold,65535].
method
setFromModelZoo(self, description: depthai.NNModelDescription, useCached: bool)
Download model from zoo and set it for this Node  Parameter ``description:``:     Model description to download  Parameter ``useCached:``:     Use cached model if available
method
setModelPath(self, modelPath: os.PathLike)
Load a network model into assets. DLC and other custom model files are loaded lazily and must remain available and unchanged until the pipeline has been built.  Parameter ``modelPath``:     Path to the model file.
method
method
setNumInferenceThreads(self, numThreads: int)
How many threads should the node use to run the network.  Parameter ``numThreads``:     Number of threads to dedicate to this node
method
setNumNCEPerInferenceThread(self, numNCEPerThread: int)
How many Neural Compute Engines should a single thread use for inference  Parameter ``numNCEPerThread``:     Number of NCE per thread
method
setNumPoolFrames(self, numFrames: int)
Specifies how many frames will be available in the pool  Parameter ``numFrames``:     How many frames will pool have
method
setNumShavesPerInferenceThread(self, numShavesPerInferenceThread: int)
How many Shaves should a single thread use for inference  Parameter ``numShavesPerThread``:     Number of shaves per thread
method
setSpatialCalculationAlgorithm(self, calculationAlgorithm: depthai.SpatialLocationCalculatorAlgorithm)
Specifies spatial location calculator algorithm: Average/Min/Max  Parameter ``calculationAlgorithm``:     Calculation algorithm.
property
property
input
Input message with data to be inferred upon
property
inputDepth
Input message with depth data used to retrieve spatial information about detected object Default queue is non-blocking with size 4
property
property
out
Outputs ImgDetections message that carries parsed detection results.
property
outNetwork
Outputs unparsed inference results.
property
passthrough
Passthrough message on which the inference was performed.  Suitable for when input queue is set to non-blocking behavior.
property
passthroughDepth
Passthrough message for depth frame on which the spatial location calculation was performed. Suitable for when input queue is set to non-blocking behavior.
property
class

depthai.node.ObjectTracker(depthai.DeviceNode)

method
setDetectionLabelsToTrack(self, labels: list[int])
Specify detection labels to track.  Parameter ``labels``:     Detection labels to track. Default every label is tracked from image     detection network output.
method
setMaxObjectsToTrack(self, maxObjectsToTrack: int)
Specify maximum number of object to track.  Parameter ``maxObjectsToTrack``:     Maximum number of object to track. Maximum 60 in case of SHORT_TERM_KCF,     otherwise 1000.
method
setOcclusionRatioThreshold(self, threshold: float)
Set the occlusion ratio threshold. Used to filter out overlapping tracklets.  Parameter ``theshold``:     Occlusion ratio threshold. Default 0.3.
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on device.
method
setSpatialAssociation(self, enabled: bool)
Enable or disable spatially-aware association. If disabled, only 2D association is used.  Parameter ``enabled``:     `true` enables spatially-aware association, `false` uses 2D-only     association. Default is false.
method
setSpatialAssociationWeight(self, weight: float)
Set spatial association weight in [0,1].  Parameter ``weight``:     Spatial association weight in [0,1] used to blend 2D and spatial association     scores (0 = 2D-only scoring, 1 = spatial-only scoring). This weight affects     candidate scoring only; final acceptance still requires passing the 2D IoU     threshold gate. Default is 0.5.
method
setSpatialDepthAwareScale(self, scale: float)
Set depth-aware gating scale used for spatial association. Increases gating threshold with increased depth.  Parameter ``scale``:     Depth-aware gating scale factor. Default is 0.35
method
setSpatialDistanceThreshold(self, thresholdMeters: float)
Set base 3D gating threshold in meters for spatial association.  Parameter ``thresholdMeters``:     Base spatial gating distance in meters. Default is 1.5m.
method
setTrackerIdAssignmentPolicy(self, type: depthai.TrackerIdAssignmentPolicy)
Specify tracker ID assignment policy.  Parameter ``type``:     Tracker ID assignment policy.
method
setTrackerThreshold(self, threshold: float)
Specify tracker threshold.  Parameter ``threshold``:     Above this threshold the detected objects will be tracked. Default 0, all     image detections are tracked.
method
setTrackerType(self, type: depthai.TrackerType)
Specify tracker type algorithm.  Parameter ``type``:     Tracker type.
method
setTrackingPerClass(self, trackingPerClass: bool)
Whether tracker should take into consideration class label for tracking.
method
setTrackletBirthThreshold(self, trackletBirthThreshold: int)
Set the tracklet birth threshold. Minimum consecutive tracked frames required to consider a tracklet as a new (TRACKED) instance.  Parameter ``trackletBirthThreshold``:     Tracklet birth threshold. Default 3.
method
setTrackletMaxLifespan(self, trackletMaxLifespan: int)
Set the tracklet lifespan in number of frames. Number of frames after which a LOST tracklet is removed.  Parameter ``trackletMaxLifespan``:     Tracklet lifespan in number of frames. Default 120.
property
inputConfig
Input ObjectTrackerConfig message with ability to modify parameters at runtime. Default queue is non-blocking with size 4.
property
inputDetectionFrame
Input ImgFrame message on which object detection was performed. Default queue is non-blocking with size 4.
property
inputDetections
Input message with image detection from neural network. Default queue is non- blocking with size 4.
property
inputTrackerFrame
Input ImgFrame message on which tracking will be performed. RGBp, BGRp, NV12, YUV420p types are supported. Default queue is non-blocking with size 4.
property
out
Outputs Tracklets message that carries object tracking results.
property
passthroughDetectionFrame
Passthrough ImgFrame message on which object detection was performed. Suitable for when input queue is set to non-blocking behavior.
property
passthroughDetections
Passthrough image detections message from neural network output. Suitable for when input queue is set to non-blocking behavior.
property
passthroughTrackerFrame
Passthrough ImgFrame message on which tracking was performed. Suitable for when input queue is set to non-blocking behavior.
class

depthai.node.IMU(depthai.DeviceNode)

method
enableFirmwareUpdate(self, arg0: bool)
Whether to perform firmware update or not. Default value: false.
method
method
getBatchReportThreshold(self) -> int: int
Above this packet threshold data will be sent to host, if queue is not blocked
method
getMaxBatchReports(self) -> int: int
Maximum number of IMU packets in a batch report
method
setBatchReportThreshold(self, batchReportThreshold: int)
Above this packet threshold data will be sent to host, if queue is not blocked
method
setMaxBatchReports(self, maxBatchReports: int)
Maximum number of IMU packets in a batch report
property
mockIn
Mock IMU data for replaying recorded data
property
out
Outputs IMUData message that carries IMU packets.
class

depthai.node.EdgeDetector(depthai.DeviceNode)

method
setMaxOutputFrameSize(self, arg0: int)
Specify maximum size of output image.  Parameter ``maxFrameSize``:     Maximum frame size in bytes
method
setNumFramesPool(self, arg0: int)
Specify number of frames in pool.  Parameter ``numFramesPool``:     How many frames should the pool have
property
initialConfig
Initial config to use for edge detection.
property
inputConfig
Input EdgeDetectorConfig message with ability to modify parameters in runtime. Default queue is non-blocking with size 4.
property
inputImage
Input image on which edge detection is performed. Default queue is non-blocking with size 4.
property
outputImage
Outputs image frame with detected edges
class

depthai.node.FeatureTracker(depthai.DeviceNode)

method
setHardwareResources(self, numShaves: int, numMemorySlices: int)
Specify allocated hardware resources for feature tracking. 2 shaves/memory slices are required for optical flow, 1 for corner detection only.  Parameter ``numShaves``:     Number of shaves. Maximum 2.  Parameter ``numMemorySlices``:     Number of memory slices. Maximum 2.
property
initialConfig
Initial config to use for feature tracking.
property
inputConfig
Input FeatureTrackerConfig message with ability to modify parameters in runtime. Default queue is non-blocking with size 4.
property
inputImage
Input message with frame data on which feature tracking is performed. Default queue is non-blocking with size 4.
property
outputFeatures
Outputs TrackedFeatures message that carries tracked features results.
property
passthroughInputImage
Passthrough message on which the calculation was performed. Suitable for when input queue is set to non-blocking behavior.
class

depthai.node.AprilTag(depthai.DeviceNode)

method
getNumThreads(self) -> int: int
Get number of threads to use for AprilTag detection.  Returns:     Number of threads to use.
method
getWaitForConfigInput(self) -> bool: bool
Get whether or not wait until configuration message arrives to inputConfig Input.
method
runOnHost(self) -> bool: bool
Check if the node is set to run on host
method
setNumThreads(self, numThreads: int)
Set number of threads to use for AprilTag detection.  Parameter ``numThreads``:     Number of threads to use.
method
setRunOnHost(self, arg0: bool)
Specify whether to run on host or device By default, the node will run on device.
method
setWaitForConfigInput(self, wait: bool)
Specify whether or not wait until configuration message arrives to inputConfig Input.  Parameter ``wait``:     True to wait for configuration message, false otherwise.
property
initialConfig
Initial config to use when calculating spatial location data.
property
inputConfig
Input AprilTagConfig message with ability to modify parameters in runtime. Default queue is non-blocking with size 4.
property
inputImage
Input message with depth data used to retrieve spatial information about detected object. Default queue is non-blocking with size 4.
property
out
Outputs AprilTags message that carries spatial location results.
property
passthroughInputImage
Passthrough message on which the calculation was performed. Suitable for when input queue is set to non-blocking behavior.
class

depthai.node.DetectionParser(depthai.DeviceNode)

method
method
getAnchorMasks(self) -> dict[str, list[int]]: dict[str, list[int]]
Get anchor masks for anchor-based yolo models
method
getAnchors(self) -> list[float]: list[float]
Get anchors for anchor-based yolo models
method
method
getConfidenceThreshold(self) -> float: float
Retrieves threshold at which to filter the rest of the detections.  Returns:     Detection confidence
method
getCoordinateSize(self) -> int: int
Get number of coordinates per bounding box.
method
getDecodeKeypoints(self) -> bool: bool
Get whether keypoints decoding is enabled.
method
getDecodeSegmentation(self) -> bool: bool
Get whether segmentation mask decoding is enabled.
method
getIouThreshold(self) -> float: float
Get IOU threshold for non-maxima suppression
method
method
getNkeypoints(self) -> int: int
Get number of keypoints to decode.
method
getNumClasses(self) -> int: int
Get number of classes to decode.
method
getNumFramesPool(self) -> int: int
Returns number of frames in pool
method
getStrides(self) -> list[int]: list[int]
Get strides for yolo models
method
getSubtype(self) -> str: str
Get subtype for the parser.
method
runOnHost(self) -> bool: bool
Check if the node is set to run on host
method
setAnchorMasks(self, anchorMasks: dict[str, list[int]])
Set anchor masks for anchor-based yolo models  Parameter ``anchorMasks``:     Map of anchor masks
method
method
method
setBlobPath(self, path: os.PathLike)
Load network blob into assets and use once pipeline is started.  Throws:     Error if file doesn't exist or isn't a valid network blob.  Parameter ``path``:     Path to network blob
method
setClasses(self, classes: list[str])
Set class names. This will clear any previously set number of classes.  Parameter ``classes``:     Vector of class names
method
setConfidenceThreshold(self, thresh: float)
Specifies confidence threshold at which to filter the rest of the detections.  Parameter ``thresh``:     Detection confidence must be greater than specified threshold to be added to     the list @note Sets startup configuration. Send DetectionParserConfig to     inputConfig for runtime updates.
method
setCoordinateSize(self, coordinates: int)
Sets the number of coordinates per bounding box.  Parameter ``coordinates``:     Number of coordinates. Default is 4
method
setDecodeKeypoints(self, decode: bool)
Enable/disable keypoints decoding. If enabled, number of keypoints must also be set.
method
setDecodeSegmentation(self, decode: bool)
Enable/disable segmentation mask decoding.
method
method
setIouThreshold(self, thresh: float)
Set IOU threshold for non-maxima suppression  Parameter ``thresh``:     IOU threshold @note Sets startup configuration. Send DetectionParserConfig     to inputConfig for runtime updates.
method
setKeypointEdges(self, edges: list[typing.Annotated[list[int], pybind11_stubgen.typing_ext.FixedSize(2)]])
Set edges connections between keypoints.  Parameter ``edges``:     Vector edges connections represented as pairs of keypoint indices. @note     This is only applicable if keypoints decoding is enabled.
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node. If the archive's type is SUPERBLOB, use default number of shaves.  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node.  Parameter ``head:``:     NNArchive head to set
method
setNNFamily(self, type: depthai.DetectionNetworkType)
Sets NN Family to parse. Possible values are:  DetectionNetworkType::YOLO - 0 DetectionNetworkType::MOBILENET - 1  .. warning::     If NN Family is set manually, user must ensure that it matches the actual     model being used.
method
setNumClasses(self, numClasses: int)
Set number of classes. This will clear any previously set class names.  Parameter ``numClasses``:     Number of classes
method
setNumFramesPool(self, numFramesPool: int)
Specify number of frames in pool.  Parameter ``numFramesPool``:     How many frames should the pool have
method
setNumKeypoints(self, numKeypoints: int)
Set number of keypoints to decode. Automatically enables keypoints decoding.
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on device.
method
setStrides(self, strides: list[int])
Set strides for yolo models
method
setSubtype(self, subtype: str)
Set subtype for the parser.  Parameter ``subtype``:     Subtype string, currently supported subtypes are: yolov6r1, yolov6r2     yolov8n, yolov6, yolov8, yolov10, yolov11, yolov3, yolov3-tiny, yolov5,     yolov7, yolo-p, yolov5-u
property
initialConfig
Initial runtime thresholds. Send a config to inputConfig to change them after startup.
property
input
Input NN results with detection data to parse Default queue is blocking with size 5
property
inputConfig
Runtime threshold configuration. Non-blocking queue of size 4; does not wait by default.
property
out
Outputs image frame with detected edges
class

depthai.node.SegmentationParser(depthai.DeviceNode)

method
method
getBackgroundClass(self) -> bool: bool
Gets whether the first class (index 0) is considered the background class.
method
getLabels(self) -> list[str]: list[str]
Returns the class labels associated with the segmentation mask.
method
runOnHost(self) -> bool: bool
Check if the node is set to run on host
method
setBackgroundClass(self, backgroundClass: bool)
Sets whether the first class (index 0) is considered the background class. If true, the pixels classified as index 0 will be treated as background.  Parameter ``backgroundClass``:     Boolean indicating if the first class is the background class  @note Only applicable if the number of classes is greater than 1 and the output classes are not in a single layer (eg. classesInOneLayer = false).
method
setLabels(self, labels: list[str])
Sets the class labels associated with the segmentation mask. The label at index $i$ in the `labels` vector corresponds to the value $i$ in the segmentation mask data array.  Parameter ``labels``:     Vector of class labels
method
setNNArchive(self, nnArchive: depthai.NNArchive)
Set NNArchive for this Node.  Parameter ``nnArchive:``:     NNArchive to set
method
setNNArchiveHead(self, head: depthai.nn_archive.v1.Head)
Set NNArchive head for this Node.  Parameter ``head:``:     NNArchive head to set
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on device.
property
initialConfig
Initial config to use when parsing segmentation masks.
property
input
Input NN results with segmentation data to parser
property
inputConfig
Input SegmentationParserConfig message with ability to modify parameters in runtime.
property
out
Outputs segmentation mask
class

depthai.node.UVC(depthai.DeviceNode)

method
setGpiosOnInit(self, list: dict[int, int])
Set GPIO list <gpio_number, value> for GPIOs to set (on/off) at init
method
setGpiosOnStreamOff(self, list: dict[int, int])
Set GPIO list <gpio_number, value> for GPIOs to set when streaming is disabled
method
setGpiosOnStreamOn(self, list: dict[int, int])
Set GPIO list <gpio_number, value> for GPIOs to set when streaming is enabled
property
input
Input for image frames to be streamed over UVC Default queue is blocking with size 8
class

depthai.node.Thermal(depthai.DeviceNode)

method
method
getBoardSocket(self) -> depthai.CameraBoardSocket: depthai.CameraBoardSocket
Retrieves which board socket to use  Returns:     Board socket to use
property
color
Outputs YUV422i grayscale thermal image.
property
initialConfig
Initial config to use for thermal sensor.
property
inputConfig
Input ThermalConfig message with ability to modify parameters in runtime. Default queue is non-blocking with size 4.
property
temperature
Outputs FP16 (degC) thermal image.
class

depthai.node.ToFBase(depthai.DeviceNode)

method
method
getBoardSocket(self) -> depthai.CameraBoardSocket: depthai.CameraBoardSocket
Retrieves which board socket to use  Returns:     Board socket to use
method
setOutputUndistortion(self, enable: bool) -> ToFBase: ToFBase
Enable or disable undistortion for depth and auxiliary outputs.  Parameter ``enable``:     Whether to undistort the outputs. @note Undistortion is supported on RVC4.     RVC2 logs a warning and leaves outputs unchanged.  Returns:     This ToF base node.
property
property
property
property
initialConfig
Initial config to use for feature tracking.
property
inputConfig
Input ToFConfig message with ability to modify parameters in runtime. Default queue is non-blocking with size 4.
property
property
property
class

depthai.node.ToF(depthai.DeviceNodeGroup)

static method
method
method
method
method
setOutputUndistortion(self, enable: bool) -> ToF: ToF
Enable or disable undistortion for depth and auxiliary outputs.  Parameter ``enable``:     Whether to undistort the outputs. @note Undistortion is supported on RVC4.     RVC2 logs a warning and leaves outputs unchanged.  Returns:     This ToF node.
property
amplitude
Amplitude output
property
confidence
Confidence output
property
depth
Filtered depth output
property
imageFiltersInputConfig
Input config for image filters
property
imageFiltersNode
Image filters node
property
intensity
Intensity output
property
phase
Phase output
property
raw
Raw data coming from the sensor
property
rawDepth
Raw depth output from ToF sensor. On RVC2 this is connected to the unfiltered base depth output. On RVC4 this is an unconnected placeholder output.
property
tofBaseInputConfig
Input config for ToF base node
property
tofBaseNode
ToF base node
class

depthai.node.PointCloud(depthai.DeviceNode)

method
setNumFramesPool(self, numFramesPool: int)
Specify number of frames in pool.  Parameter ``numFramesPool``:     How many frames should the pool have
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on host.
method
method
useCPU(self)
Use single-threaded CPU for processing
method
useCPUMT(self, numThreads: int = 2)
Use multi-threaded CPU for processing
method
useGPU(self, device: int = 0)
Use GPU for point cloud computation  Parameter ``device``:     GPU device index (default 0)
property
initialConfig
Initial config to use when computing the point cloud.
property
property
inputConfig
Input PointCloudConfig message with ability to modify parameters in runtime. Default queue is non-blocking with size 4.
property
property
outputPointCloud
Outputs PointCloudData message
property
passthroughDepth
Passthrough depth from which the point cloud was calculated. Suitable for when input queue is set to non-blocking behavior.
class

depthai.node.Sync(depthai.DeviceNode)

class
TimestampSource
Members:    DEFAULT    DEVICE    HOST    SYSTEM
method
getProcessor(self) -> depthai.ProcessorType: depthai.ProcessorType
Get on which processor the node should run  Returns:     Processor type - Leon CSS or Leon MSS
method
getSyncAttempts(self) -> int: int
Gets the number of sync attempts
method
getSyncThreshold(self) -> datetime.timedelta: datetime.timedelta
Gets the maximal interval between messages in the group in milliseconds
method
method
runOnHost(self) -> bool: bool
Check if the node is set to run on host
method
setProcessor(self, processorType: depthai.ProcessorType)
Specify on which processor the node should run. RVC2 only.  Parameter ``type``:     Processor type - Leon CSS or Leon MSS
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on device.
method
setSyncAttempts(self, maxDataSize: int)
Set the number of attempts to get the specified max interval between messages in the group  Parameter ``syncAttempts``:     Number of attempts to get the specified max interval between messages in the     group: - if syncAttempts = 0 then the node sends a message as soon at the     group is filled - if syncAttempts > 0 then the node will make syncAttemts     attempts to synchronize before sending out a message - if syncAttempts = -1     (default) then the node will only send a message if successfully     synchronized
method
setSyncThreshold(self, syncThreshold: datetime.timedelta)
Set the maximal interval between messages in the group  Parameter ``syncThreshold``:     Maximal interval between messages in the group
method
property
inputs
A map of inputs
property
class

depthai.node.MessageDemux(depthai.DeviceNode)

method
getProcessor(self) -> depthai.ProcessorType: depthai.ProcessorType
Get on which processor the node should run  Returns:     Processor type - Leon CSS or Leon MSS
method
runOnHost(self) -> bool: bool
Check if the node is set to run on host
method
setProcessor(self, arg0: depthai.ProcessorType)
Specify on which processor the node should run. RVC2 only.  Parameter ``type``:     Processor type - Leon CSS or Leon MSS
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on device.
property
input
Input message of type MessageGroup
property
outputs
A map of outputs, where keys are same as in the input MessageGroup
class

depthai.node.HostNode(depthai.node.ThreadedHostNode)

CLASS_METHOD
method
method
method
method
method
method
method
method
sendProcessingToPipeline(self, arg0: bool)
Send processing to pipeline. If set to true, it's important to call `pipeline.run()` in the main thread or `pipeline.processTasks()` in the main thread. Otherwise, if set to false, such action is not needed.
property
property
class

depthai.node.RecordMetadataOnly(depthai.node.ThreadedHostNode)

class

depthai.node.ImageFilters(depthai.DeviceNode)

method
method
runOnHost(self) -> bool: bool
Check if the node is set to run on host
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on device.
property
initialConfig
Initial config for image filters.
property
input
Input for image frames to be filtered
property
inputConfig
Config to be set for a specific filter
property
output
Filtered frame
class

depthai.node.ToFDepthConfidenceFilter(depthai.DeviceNode)

method
method
runOnHost(self) -> bool: bool
Check if the node is set to run on host
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on device.
property
amplitude
Amplitude frame image, expected ImgFrame type is RAW8 or RAW16.
property
confidence
RAW16 encoded confidence frame
property
depth
Depth frame image, expected ImgFrame type is RAW8 or RAW16.
property
filteredDepth
RAW16 encoded filtered depth frame
property
initialConfig
Initial config for ToF depth confidence filter.
property
inputConfig
Config message for runtime filter configuration
class

depthai.node.ReplayMetadataOnly(depthai.node.ThreadedHostNode)

class

depthai.node.ImageAlign(depthai.DeviceNode)

method
runOnHost(self) -> bool: bool
Check if the node is set to run on host
method
method
method
setNumShaves(self, numShaves: int) -> ImageAlign: ImageAlign
Specify number of shaves to use for this node
method
setOutKeepAspectRatio(self, keep: bool) -> ImageAlign: ImageAlign
Specify whether to keep aspect ratio when resizing
method
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on device.
property
initialConfig
Initial config to use when calculating spatial location data.
property
input
Input message. Default queue is non-blocking with size 4.
property
inputAlignTo
Input align to message. Default queue is non-blocking with size 1.
property
inputConfig
Input message with ability to modify parameters in runtime. Default queue is non-blocking with size 4.
property
outputAligned
Outputs ImgFrame message that is aligned to inputAlignTo.
property
passthroughInput
Passthrough message on which the calculation was performed. Suitable for when input queue is set to non-blocking behavior.
class

depthai.node.Align(depthai.DeviceNode)

method
runOnHost(self) -> bool: bool
Check if the node is set to run on host
method
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on device.
property
initialConfig
Initial config to use when aligning messages.
property
input
Input message to be aligned. Can be either ImgFrame or any message that implements Transformable interface. Default queue is non-blocking with size 4.
property
inputAlignTo
Input align to message. Default queue is non-blocking with size 1.
property
inputConfig
Input message with ability to modify parameters in runtime. Default queue is non-blocking with size 4.
property
outputAligned
Outputs the input message aligned to the inputAlignTo message. Output message will be of the same type as input message.
property
passthroughInput
Passthrough message on which the calculation was performed. Suitable for when input queue is set to non-blocking behavior.
class

depthai.node.RGBD(depthai.node.ThreadedHostNode)

method
method
printDevices(self)
Print available GPU devices
method
method
useCPU(self)
Use single-threaded CPU for processing
method
useCPUMT(self, numThreads: int = 2)
Use multi-threaded CPU for processing  Parameter ``numThreads``:     Number of threads to use
method
useGPU(self, device: int = 0)
Use GPU for processing (needs to be compiled with Kompute support)  Parameter ``device``:     GPU device index
property
property
property
pcl
Output point cloud.
property
rgbd
Output RGBD frames.
class

depthai.node.Rectification(depthai.DeviceNode)

method
enableRectification(self, enable: bool) -> Rectification: Rectification
Enable or disable rectification (useful for minimal changes during debugging)
method
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on device.
property
input1
Input images to be rectified
property
property
output1
Send outputs
property
property
passthrough1
Passthrough for input messages (so the node can be placed between other nodes)
property
class

depthai.node.NeuralDepth(depthai.DeviceNode)

static method
method
method
setRectification(self, enable: bool) -> NeuralDepth: NeuralDepth
Enable or disable rectification (useful for prerectified inputs)
property
confidence
Output confidence ImgFrame
property
depth
Output depth ImgFrame
property
disparity
Output disparity ImgFrame
property
edge
Output edge ImgFrame
property
initialConfig
Initial config to use for NeuralDepth.
property
inputConfig
Input config to modify parameters in runtime.
property
left
Input for left ImgFrame of left-right pair
property
property
property
property
rectifiedLeft
Output for rectified left ImgFrame
property
rectifiedRight
Output for rectified right ImgFrame
property
right
Input for right ImgFrame of left-right pair
property
class

depthai.node.GPUStereo(depthai.DeviceNode)

method
method
setRectification(self, enable: bool) -> GPUStereo: GPUStereo
Enable or disable built-in stereo rectification.  When enabled, the node rectifies the input images internally using calibration data. When disabled, inputs are expected to be already rectified.
property
confidenceMap
Outputs ImgFrame message that carries RAW8 confidence map. Lower values mean lower confidence of the calculated disparity value. Note: postprocessing steps like LR-check/median filter are not applied to confidence map.
property
depth
Outputs ImgFrame message that carries RAW16 encoded (0..65535) depth data in depth units (millimeter by default).  Non-determined / invalid depth values are set to 0
property
disparity
Outputs ImgFrame message that carries RAW16 encoded disparity data.
property
initialConfig
Initial config to use for GPUStereo.  Use this to configure startup parameters before the pipeline starts. Note: Only `confidenceThreshold` is supported/exposed for this node.
property
property
class

depthai.node.Depth(depthai.DeviceNodeGroup)

class
Algorithm
Backend selection for the Depth node.  Members:    AUTO    STEREO    NEURAL    NEURAL_ASSISTED_STEREO    TOF    TOF_STEREO_FUSION    GPU_STEREO
method
method
method
getRequestedConfig(self) -> typing.Any: typing.Any
Get the requested config override, if any.  Returns:     Config override, or std::nullopt when config is auto-picked
method
getResolvedAlgorithm(self) -> Depth.Algorithm: Depth.Algorithm
Get the algorithm actually wired (AUTO resolved). Valid after first depth() access.
method
getResolvedConfig(self) -> typing.Any: typing.Any
Get the resolved algorithm-specific config.
method
setAlgorithm(self, algorithm: Depth.Algorithm) -> Depth: Depth
Set the requested algorithm before wiring.  Parameter ``algorithm``:     Backend to use; AUTO re-enables auto-selection
method
setAlignTo(self, alignTo: depthai.Node.Output) -> Depth: Depth
Align depth output to another image source. Must be called before first depth() or confidence() access. Only depth() is aligned; confidence() stays in the backend frame.  Parameter ``alignTo``:     Output to align depth to
method
property
confidence
Output confidence map from the active backend. When ToF is active, this forwards the actual ToF confidence output.
property
depth
Output depth map from the active backend.
class

depthai.node.Vpp(depthai.DeviceNode)

method
property
property
depth
Depth input, used instead of disparity. Expects RAW16 millimetres aligned to the full rectified left image, with stereo intrinsics and extrinsics on the image frames. Requires RVC4 firmware with VPP depth-input support.
property
property
initialConfig
Initial config of the node.
method
property
property
property
leftOut
Output ImgFrame message that carries the processed left image with virtual projection pattern applied.
property
property
rightOut
Output ImgFrame message that carries the processed right image with virtual projection pattern applied.
property
syncedInputs
Synchronised left and right images with either disparity or depth, and optional confidence.
class

depthai.node.Gate(depthai.DeviceNode)

method
runOnHost(self) -> bool: bool
Check if the node is configured to run on the host.  Returns:     true if running on host, false otherwise.
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on device.
property
initialConfig
Initial config of the node.
method
property
input
Main data input. * Accepts arbitrary Buffer messages (e.g., ImgFrame, NNData). If the Gate is Open, messages received here are forwarded to 'output'. If the Gate is Closed, messages received here are discarded/dropped. * Default queue size: 1 Blocking: False
property
inputControl
Control input. * Accepts 'GateControl' messages to dynamically change the Gate's state. Use this to Open/Close the gate or set it to pass a specific number of frames at runtime. * Default queue size: 4
property
output
Main data output. * Forwards messages that were allowed through the Gate. The data type matches the input message.
class

depthai.node.RTABMapVIO(depthai.node.ThreadedHostNode)

method
method
method
method
setUseFeatures(self, useFeatures: bool)
Whether to use input features or calculate them internally.
property
property
features
Input tracked features on which VIO is performed (optional).
property
imu
Input IMU data.
property
passthroughDepth
Passthrough depth frame.
property
passthroughFeatures
Passthrough features.
property
passthroughRect
Passthrough rectified frame.
property
property
transform
Output odometry.
class

depthai.node.RTABMapSLAM(depthai.node.ThreadedHostNode)

method
method
method
setAlphaScaling(self, alpha: float)
Set the alpha scaling factor for the camera model.
method
setDatabasePath(self, path: str)
Set RTABMap database path. "/tmp/rtabmap.tmp.db" by default.
method
setFreq(self, f: float)
Set the frequency at which the node processes data. 1Hz by default.
method
setLoadDatabaseOnStart(self, load: bool)
Whether to load the database on start. False by default.
method
method
setParams(self, params: dict[str, str])
Set RTABMap parameters. For the list of all parameters visit  https://github.com/introlab/rtabmap/blob/master/corelib/include/rtabmap/core/Par ameters.h
method
setPublishGrid(self, publish: bool)
Whether to publish the ground point cloud. True by default.
method
setPublishGroundCloud(self, publish: bool)
Whether to publish the ground point cloud. True by default.
method
setPublishObstacleCloud(self, publish: bool)
Whether to publish the obstacle point cloud. True by default.
method
setSaveDatabaseOnClose(self, save: bool)
Whether to save the database on close. False by default.
method
setSaveDatabasePeriod(self, period: float)
Set the interval at which the database is saved. 30.0s by default.
method
setSaveDatabasePeriodically(self, save: bool)
Whether to save the database periodically. False by default.
method
setUseFeatures(self, useFeatures: bool)
Whether to use input features for SLAM. False by default.
method
triggerNewMap(self)
Trigger a new map.
property
property
features
Input tracked features on which SLAM is performed (optional).
property
groundPCL
Output ground point cloud.
property
obstaclePCL
Output obstacle point cloud.
property
occupancyGridMap
Output occupancy grid map.
property
odom
Input odometry pose.
property
odomCorrection
Output odometry correction (map to odom).
property
passthroughDepth
Output passthrough depth image.
property
passthroughFeatures
Output passthrough features.
property
passthroughOdom
Output passthrough odometry pose.
property
passthroughRect
Output passthrough rectified image.
property
property
transform
Output transform.
class

depthai.node.DynamicCalibration(depthai.DeviceNode)

method
method
setRunOnHost(self, runOnHost: bool)
Specify whether to run on host or device By default, the node will run on host on RVC2 and on device on RVC4.
property
calibrationOutput
Output calibration quality result
property
property
inputControl
Input DynamicCalibrationControl message with ability to modify parameters in runtime.
property
property
property
property
property
property
property
class

depthai.HousingCoordinateSystem

variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
method
method
method
method
method
method
method
method
method
method
property
property
class

depthai.CameraSensorConfig

class

depthai.MemoryInfo

class

depthai.ChipTemperature

variable
variable
variable
variable
variable
method
class

depthai.ChipTemperatureRVC4

class

depthai.CpuUsage

class

depthai.Extrinsics

variable
variable
variable
variable
variable
variable
method
method
getExtrinsicsTransformationTo(self, to: Extrinsics, useSpecTranslation: bool = False, unit: LengthUnit = ...) -> typing.Annotated[list[typing.Annotated[list[float], pybind11_stubgen.typing_ext.FixedSize(4)]], pybind11_stubgen.typing_ext.FixedSize(4)]: typing.Annotated[list[typing.Annotated[list[float], pybind11_stubgen.typing_ext.FixedSize(4)]], pybind11_stubgen.typing_ext.FixedSize(4)]
Get the extrinsic transformation matrix from this Extrinsics to the target Extrinsics.  Parameter ``to``:     The target Extrinsics to get the transformation matrix to  Parameter ``useSpecTranslation``:     Set to true to force using spec translation  Parameter ``sourceUnit``:     Units of the translation vector in the source Extrinsics (this). Only     relevant if useSpecTranslation is false.  Returns:     a transformationMatrix which is 4x4 in homogeneous coordinate system
method
getInverseRotationMatrix(self) -> list[list[float]]: list[list[float]]
Get the inverse extrinsic rotation matrix in array format.  Returns:     3x3 inverse rotation matrix as a 2D array
method
getInverseTransformationMatrix(self, useSpecTranslation: bool = False, unit: LengthUnit = ...) -> typing.Annotated[list[typing.Annotated[list[float], pybind11_stubgen.typing_ext.FixedSize(4)]], pybind11_stubgen.typing_ext.FixedSize(4)]: typing.Annotated[list[typing.Annotated[list[float], pybind11_stubgen.typing_ext.FixedSize(4)]], pybind11_stubgen.typing_ext.FixedSize(4)]
Get the inverse of the extrinsic transformation matrix which is equal to the transformation from the toCameraSocket to the current camera socket.  Parameter ``useSpecTranslation``:     Set to true to force using spec translation  Parameter ``unit``:     Units of the returned translation vector  Returns:     a transformationMatrix which is 4x4 in homogeneous coordinate system
method
getRotationMatrix(self) -> list[list[float]]: list[list[float]]
Get the extrinsic rotation matrix in array format.  Returns:     3x3 rotation matrix as a 2D array
method
getTransformationMatrix(self, useSpecTranslation: bool = False, unit: LengthUnit = ...) -> typing.Annotated[list[typing.Annotated[list[float], pybind11_stubgen.typing_ext.FixedSize(4)]], pybind11_stubgen.typing_ext.FixedSize(4)]: typing.Annotated[list[typing.Annotated[list[float], pybind11_stubgen.typing_ext.FixedSize(4)]], pybind11_stubgen.typing_ext.FixedSize(4)]
Get the Camera Extrinsics object to the toCameraSocket.  Parameter ``useSpecTranslation``:     Set to true to force using spec translation  Parameter ``unit``:     Units of the returned translation vector  Returns:     4x4 homogeneous transformation matrix  The returned matrix has the following layout:  ``` [ r00 r01 r02 Tx ] [ r10 r11 r12 Ty ] [ r20 r21 r22 Tz ] [  0   0   0  1 ] ```  @note The full transformation matrix can only be obtained if both the rotation matrix and the translation vector are set.
method
getTranslationVector(self, useSpecTranslation: bool = False, unit: LengthUnit = ...) -> list[float]: list[float]
Get the translation vector  Parameter ``unit``:     Units of the returned translation vector  Returns:     translation vector in specified units
method
hasCompatibleCoordinateSystem(self, to: Extrinsics) -> bool: bool
Check whether these extrinsics can be expressed relative to the same target coordinate system as another Extrinsics object. Unknown device IDs and AUTO camera sockets are treated as compatible for backwards compatibility.  Parameter ``to``:     The target Extrinsics object to compare with  Returns:     true if no known part of the target coordinate system differs, false     otherwise
method
hasValidRotationMatrix(self) -> bool: bool
Check whether the rotation matrix is a finite, proper 3x3 rotation matrix.  Returns:     true if the rotation matrix is valid, false otherwise
method
isEqualExtrinsics(self, other: Extrinsics, epsilon: float = 9.999999974752427e-07) -> bool: bool
Two Extrinsics objects are equal if their rotation matrices and translation vectors are equal (within a small epsilon).  Parameter ``other``:     The other Extrinsics object to compare with  Parameter ``epsilon``:     The tolerance for comparing floating-point values  Returns:     true if the Extrinsics objects are equal, false otherwise
method
setTransformationMatrix(self, matrix: list[list[float]], unit: LengthUnit = ...)
Set the extrinsic transformation matrix.  Parameter ``matrix``:     4x4 homogeneous transformation matrix  Parameter ``unit``:     Units of the translation components Tx, Ty, and Tz  The matrix must have the following layout:  ``` [ r00 r01 r02 Tx ] [ r10 r11 r12 Ty ] [ r20 r21 r22 Tz ] [  0   0   0  1 ] ```
method
setTranslationVector(self, translationVector: Point3f, unit: LengthUnit = ..., useSpecTranslation: bool = False)
Set the translation vector  Parameter ``translationVector``:     The translation vector to set  Parameter ``unit``:     Units of the provided translation vector  Parameter ``useSpecTranslation``:     Set to true to force setting spec translation
class

depthai.MultiDeviceExtrinsics

class

depthai.AccelerometerNoiseParams

class

depthai.GyroscopeNoiseParams

class

depthai.AccelAxisNoiseParams

class

depthai.GyroAxisNoiseParams

class

depthai.RotatedRect

variable
variable
variable
method
method
denormalize(self, width: int, height: int, force: bool = False) -> RotatedRect: RotatedRect
Denormalize the rotated rectangle. The denormalized rectangle will have center and size coordinates in range [0, width] and [0, height]  Returns:     Denormalized rotated rectangle
method
getOuterCXCYWH(self) -> tuple[Point2f, Size2f]: tuple[Point2f, Size2f]
Returns the outer non-rotated rectangle in the YOLO (xcenter, ycenter, width, height) format.  Returns:     (center point, size)
method
method
getOuterXYWH(self) -> tuple[Point2f, Size2f]: tuple[Point2f, Size2f]
Returns the outer non-rotated rectangle in the COCO (xmin, ymin, width, height) format.  Returns:     (top-left point, size)
method
method
method
normalize(self, width: int, height: int) -> RotatedRect: RotatedRect
Normalize the rotated rectangle. The normalized rectangle will have center and size coordinates in range [0,1]  Returns:     Normalized rotated rectangle
class

depthai.Rect

variable
variable
variable
variable
method
method
area(self) -> float: float
Area (width*height) of the rectangle
method
method
contains(self, point: Point2f) -> bool: bool
Checks whether the rectangle contains the point.
method
denormalize(self, width: int, height: int) -> Rect: Rect
Denormalize rectangle.  Parameter ``destWidth``:     Destination frame width.  Parameter ``destHeight``:     Destination frame height.
method
empty(self) -> bool: bool
True if rectangle is empty.
method
isNormalized(self) -> bool: bool
Whether rectangle is normalized (coordinates in [0,1] range) or not.
method
normalize(self, width: int, height: int) -> Rect: Rect
Normalize rectangle.  Parameter ``srcWidth``:     Source frame width.  Parameter ``srcHeight``:     Source frame height.
method
size(self) -> Size2f: Size2f
Size (width, height) of the rectangle
method
class

depthai.ProfilingData

class

depthai.SpatialKeypointsList

method
method
method
getKeypoints(self) -> list[SpatialKeypoint]: list[SpatialKeypoint]
Get keypoints.  Returns:     Vector of Keypoint objects.
method
getPoints2f(self) -> VectorPoint2f: VectorPoint2f
Get only image 2D coordinates of the keypoints and drop the z axis values.  Returns:     Vector of Point2f coordinates.
method
getPoints3f(self) -> list[Point3f]: list[Point3f]
Get only image coordinates of the keypoints.  Returns:     Vector of Point3f coordinates.
method
getSpatialCoordinates(self) -> list[Point3f]: list[Point3f]
Get spatial coordinates of the keypoints.  Returns:     Vector of Point3f spatial coordinates.
method
method
method
setSpatialCoordinates(self, spatialCoordinates: list[Point3f], spatialUnit: LengthUnit = ...)
Sets the keypoints from a vector of 3D spatial points.  The size of spatialCoordinates must match the number of keypoints.  Parameter ``spatialCoordinates``:     vector of Point3f objects to set as spatial coordinates.  Parameter ``spatialUnit``:     The unit of the spatial coordinates. By default, spatial coordinates are in     millimeters.
property
unit
Length unit used by all keypoints' `spatialCoordinates` in this list.
method
class

depthai.DatatypeEnum

variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
method
method
method
method
method
method
method
method
method
method
property
property
class

depthai.ADatatype

class

depthai.Buffer(depthai.ADatatype)

method
method
method
getData(self) -> numpy.ndarray[numpy.uint8]: numpy.ndarray[numpy.uint8]
Get non-owning reference to internal buffer  Returns:     Reference to internal buffer
method
method
method
getTimestampDevice(self: typing_extensions.Buffer) -> datetime.timedelta: datetime.timedelta
Retrieves timestamp directly captured from device's monotonic clock, not synchronized to host time. Used mostly for debugging
method
getTimestampSystem(self: typing_extensions.Buffer) -> datetime.datetime|None: datetime.datetime|None
Retrieves timestamp directly captured from device's system clock, that can be synchronized using PTP
method
getVisualizationMessage(self: typing_extensions.Buffer) -> ImgAnnotations|ImgFrame|None: ImgAnnotations|ImgFrame|None
Get visualizable message  Returns:     Visualizable message, either ImgFrame, ImgAnnotations or std::monostate     (None)
method
method
method
method
method
method
setTimestampSystem(self: typing_extensions.Buffer, arg0: datetime.datetime|None)
Sets optional system_clock timestamp (device system clock; may be PTP- synchronized).
class

depthai.Transformable

variable
method
getTransformation(self) -> ImgTransformation|None: ImgTransformation|None
Returns the current transformation if set, else std::nullopt.
method
class

depthai.TransformableBuffer(depthai.Buffer, depthai.Transformable)

method
method
transformTo(self, target: ImgTransformation) -> TransformableBuffer: TransformableBuffer
Returns a transformed copy of this message.  Python subclasses of TransformableBuffer should override this method to implement custom transformation logic. Generic callers use this entry point when they need to transform a custom message without knowing its concrete type. The base implementation throws, because it cannot preserve Python subclass state automatically.  Parameter ``target``:     Target image transformation.
class

depthai.AprilTagConfig(depthai.Buffer)

class
Family
Supported AprilTag families.  Members:    TAG_36H11    TAG_36H10    TAG_25H9    TAG_16H5    TAG_CIR21H7    TAG_STAND41H12
class
QuadThresholds
AprilTag quad threshold parameters.
method
method
method
property
decodeSharpening
How much sharpening should be done to decoded images? This can help decode small tags but may or may not help in odd lighting conditions or low light conditions. The default value is 0.25.
method
property
family
AprilTag family.
method
property
maxHammingDistance
Max number of error bits that should be corrected. Accepting large numbers of corrected errors leads to greatly increased false positive rates. As of this implementation, the detector cannot detect tags with a hamming distance greater than 2.
method
property
quadDecimate
Detection of quads can be done on a lower-resolution image, improving speed at a cost of pose accuracy and a slight decrease in detection rate. Decoding the binary payload is still done at full resolution.
method
property
quadSigma
What Gaussian blur should be applied to the segmented image. Parameter is the standard deviation in pixels. Very noisy images benefit from non-zero values (e.g. 0.8).
method
property
quadThresholds
AprilTag quad threshold parameters.
method
property
refineEdges
When non-zero, the edges of the each quad are adjusted to "snap to" strong gradients nearby. This is useful when decimation is employed, as it can increase the quality of the initial quad estimate substantially. Generally recommended to be on. Very computationally inexpensive. Option is ignored if quadDecimate = 1.
method
class

depthai.AprilTagConfig.QuadThresholds

method
property
criticalDegree
Reject quads where pairs of edges have angles that are close to straight or close to 180 degrees. Zero means that no quads are rejected. (In degrees).
method
property
deglitch
Should the thresholded image be deglitched? Only useful for very noisy images
method
property
maxLineFitMse
When fitting lines to the contours, what is the maximum mean squared error allowed? This is useful in rejecting contours that are far from being quad shaped; rejecting these quads "early" saves expensive decoding processing.
method
property
maxNmaxima
How many corner candidates to consider when segmenting a group of pixels into a quad.
method
property
minClusterPixels
Reject quads containing too few pixels.
method
property
minWhiteBlackDiff
When we build our model of black & white pixels, we add an extra check that the white model must be (overall) brighter than the black model. How much brighter? (in pixel values: [0,255]).
method
class

depthai.AprilTag

method
property
bottomLeft
The detected bottom left coordinates.
method
property
bottomRight
The detected bottom right coordinates.
method
property
decisionMargin
A measure of the quality of the binary decoding process; the average difference between the intensity of a data bit versus the decision threshold. Higher numbers roughly indicate better decodes. This is a reasonable measure of detection accuracy only for very small tags-- not effective for larger tags (where we could have sampled anywhere within a bit cell and still gotten a good detection.
method
property
hamming
How many error bits were corrected? Note: accepting large numbers of corrected errors leads to greatly increased false positive rates. As of this implementation, the detector cannot detect tags with a hamming distance greater than 2.
method
property
id
The decoded ID of the tag
method
property
topLeft
The detected top left coordinates.
method
property
topRight
The detected top right coordinates.
method
class

depthai.AprilTags(depthai.Buffer, depthai.Transformable)

variable
method
method
method
transformTo(self, target: ImgTransformation) -> AprilTags: AprilTags
Returns a new AprilTags message with the tags transformed into the target image transformation.  If the target transformation has a different coordinate system source (eg. different camera socket) then the remapping will be inaccurate due to the lack of depth information.  Parameter ``target``:     Target image transformation.
class

depthai.CameraControl(depthai.Buffer)

class
Command
Members:    START_STREAM    STOP_STREAM    STILL_CAPTURE    MOVE_LENS    AF_TRIGGER    AE_MANUAL    AE_AUTO    AWB_MODE    SCENE_MODE    ANTIBANDING_MODE    EXPOSURE_COMPENSATION    AE_LOCK    AE_TARGET_FPS_RANGE    AWB_LOCK    CAPTURE_INTENT    CONTROL_MODE    FRAME_DURATION    SENSITIVITY    EFFECT_MODE    AF_MODE    NOISE_REDUCTION_STRENGTH    SATURATION    BRIGHTNESS    STREAM_FORMAT    RESOLUTION    SHARPNESS    CUSTOM_USECASE    CUSTOM_CAPT_MODE    CUSTOM_EXP_BRACKETS    CUSTOM_CAPTURE    CONTRAST    AE_REGION    AF_REGION    LUMA_DENOISE    CHROMA_DENOISE    WB_COLOR_TEMP    AE_MAX_ISO
class
AutoFocusMode
Members:    OFF    AUTO    MACRO    CONTINUOUS_VIDEO    CONTINUOUS_PICTURE    EDOF
class
AutoWhiteBalanceMode
Members:    OFF    AUTO    INCANDESCENT    FLUORESCENT    WARM_FLUORESCENT    DAYLIGHT    CLOUDY_DAYLIGHT    TWILIGHT    SHADE
class
SceneMode
Members:    UNSUPPORTED    FACE_PRIORITY    ACTION    PORTRAIT    LANDSCAPE    NIGHT    NIGHT_PORTRAIT    THEATRE    BEACH    SNOW    SUNSET    STEADYPHOTO    FIREWORKS    SPORTS    PARTY    CANDLELIGHT    BARCODE
class
ControlMode
Members:    OFF    AUTO    USE_SCENE_MODE
class
CaptureIntent
Members:    CUSTOM    PREVIEW    STILL_CAPTURE    VIDEO_RECORD    VIDEO_SNAPSHOT    ZERO_SHUTTER_LAG
class
AntiBandingMode
Members:    OFF    MAINS_50_HZ    MAINS_60_HZ    AUTO
class
EffectMode
Members:    OFF    MONO    NEGATIVE    SOLARIZE    SEPIA    POSTERIZE    WHITEBOARD    BLACKBOARD    AQUA
class
FrameSyncMode
Members:    AUTO    OFF    OUTPUT    INPUT    TIME_PTP
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
method
method
method
method
clearMiscControls(self)
Clear the list of miscellaneous controls set by `setControl`
method
getCaptureStill(self) -> bool: bool
Check whether command to capture a still is set  Returns:     True if capture still command is set
method
method
method
getHdr(self) -> bool: bool
Whether or not HDR (High Dynamic Range) mode is enabled  Returns:     True if HDR mode is enabled, false otherwise
method
getLensPosition(self) -> int: int
Retrieves lens position, range 0..255. Returns -1 if not available
method
getLensPositionRaw(self) -> float: float
Retrieves lens position, range 0.0f..1.0f.
method
getMiscControls(self) -> list[tuple[str, str]]: list[tuple[str, str]]
Get the list of miscellaneous controls set by `setControl`  Returns:     A list of <key, value> pairs as strings
method
getSensitivity(self) -> int: int
Retrieves sensitivity, as an ISO value
method
setAntiBandingMode(self, mode: CameraControl.AntiBandingMode) -> CameraControl: CameraControl
Set a command to specify anti-banding mode. Anti-banding / anti-flicker works in auto-exposure mode, by controlling the exposure time to be applied in multiples of half the mains period, for example in multiple of 10ms for 50Hz (period 20ms) AC-powered illumination sources.  If the scene would be too bright for the smallest exposure step (10ms in the example, with ISO at a minimum of 100), anti-banding is not effective.  Parameter ``mode``:     Anti-banding mode to use. Default: `MAINS_50_HZ`
method
setAutoExposureCompensation(self, compensation: int) -> CameraControl: CameraControl
Set a command to specify auto exposure compensation. This modifies the brightness target with positive numbers making the image brighter and negative numbers making the image darker.  Parameter ``compensation``:     Compensation value between -9..9, default 0
method
method
method
setAutoExposureLock(self, lock: bool) -> CameraControl: CameraControl
Set a command to stop the auto-exposure algorithm. The latest AE sensor configuration is kept.  Parameter ``lock``:     Auto exposure lock mode enabled or disabled
method
setAutoExposureMaxISO(self, aeMaxISO: int) -> CameraControl: CameraControl
Set a command to specify the maximum ISO sensitivity limit for auto-exposure. This limits the AE algorithm from increasing sensitivity beyond a certain point and can help to reduce noise in low-light conditions.  Parameter ``aeMaxISO``:     Maximum ISO
method
setAutoExposureRegion(self, startX: int, startY: int, width: int, height: int) -> CameraControl: CameraControl
Set a command to specify auto exposure region in pixels. Note: the region should be mapped to the configured sensor resolution, before ISP scaling  Parameter ``startX``:     X coordinate of top left corner of region  Parameter ``startY``:     Y coordinate of top left corner of region  Parameter ``width``:     Region width  Parameter ``height``:     Region height
method
setAutoFocusLensRange(self, infinityPosition: int, macroPosition: int) -> CameraControl: CameraControl
Set autofocus lens range, `infinityPosition < macroPosition`, valid values `0..255`. May help to improve autofocus in case the lens adjustment is not typical/tuned
method
setAutoFocusMode(self, mode: CameraControl.AutoFocusMode) -> CameraControl: CameraControl
Set a command to specify autofocus mode. Default `CONTINUOUS_VIDEO`
method
setAutoFocusRegion(self, startX: int, startY: int, width: int, height: int) -> CameraControl: CameraControl
Set a command to specify focus region in pixels. Note: the region should be mapped to the configured sensor resolution, before ISP scaling  Parameter ``startX``:     X coordinate of top left corner of region  Parameter ``startY``:     Y coordinate of top left corner of region  Parameter ``width``:     Region width  Parameter ``height``:     Region height
method
method
setAutoWhiteBalanceLock(self, lock: bool) -> CameraControl: CameraControl
Set a command to specify auto white balance lock  Parameter ``lock``:     Auto white balance lock mode enabled or disabled
method
setAutoWhiteBalanceMode(self, mode: CameraControl.AutoWhiteBalanceMode) -> CameraControl: CameraControl
Set a command to specify auto white balance mode  Parameter ``mode``:     Auto white balance mode to use. Default `AUTO`
method
setBrightness(self, value: int) -> CameraControl: CameraControl
Set a command to adjust image brightness  Parameter ``value``:     Brightness, range -10..10, default 0
method
setCaptureIntent(self, mode: CameraControl.CaptureIntent) -> CameraControl: CameraControl
Set a command to specify capture intent mode  Parameter ``mode``:     Capture intent mode
method
method
setChromaDenoise(self, value: int) -> CameraControl: CameraControl
Set a command to adjust chroma denoise amount  Parameter ``value``:     Chroma denoise amount, range 0..4, default 1
method
method
setContrast(self, value: int) -> CameraControl: CameraControl
Set a command to adjust image contrast  Parameter ``value``:     Contrast, range -10..10, default 0
method
setControlMode(self, mode: CameraControl.ControlMode) -> CameraControl: CameraControl
Set a command to specify control mode  Parameter ``mode``:     Control mode
method
setEffectMode(self, mode: CameraControl.EffectMode) -> CameraControl: CameraControl
Set a command to specify effect mode  Parameter ``mode``:     Effect mode
method
setExternalTrigger(self, numFramesBurst: int, numFramesDiscard: int) -> CameraControl: CameraControl
Set a command to enable external trigger snapshot mode  A rising edge on the sensor FSIN pin will make it capture a sequence of `numFramesBurst` frames. First `numFramesDiscard` will be skipped as configured (can be set to 0 as well), as they may have degraded quality
method
setFrameSyncMode(self, mode: CameraControl.FrameSyncMode) -> CameraControl: CameraControl
Set the frame sync mode for continuous streaming operation mode, translating to how the camera pin FSIN/FSYNC is used: auto/input/output/disabled
method
setHdr(self, enable: bool) -> CameraControl: CameraControl
Whether or not to enable HDR (High Dynamic Range) mode  Parameter ``enable``:     True to enable HDR mode, false to disable
method
setLumaDenoise(self, value: int) -> CameraControl: CameraControl
Set a command to adjust luma denoise amount  Parameter ``value``:     Luma denoise amount, range 0..4, default 1
method
method
setManualFocus(self, lensPosition: int) -> CameraControl: CameraControl
Set a command to specify manual focus position  Parameter ``lensPosition``:     specify lens position 0..255
method
setManualFocusRaw(self, lensPositionRaw: float) -> CameraControl: CameraControl
Set a command to specify manual focus position (more precise control).  Parameter ``lensPositionRaw``:     specify lens position 0.0f .. 1.0f  Returns:     CameraControl&
method
setManualWhiteBalance(self, colorTemperatureK: int) -> CameraControl: CameraControl
Set a command to manually specify white-balance color correction  Parameter ``colorTemperatureK``:     Light source color temperature in kelvins, range 1000..12000
method
method
setSaturation(self, value: int) -> CameraControl: CameraControl
Set a command to adjust image saturation  Parameter ``value``:     Saturation, range -10..10, default 0
method
setSceneMode(self, mode: CameraControl.SceneMode) -> CameraControl: CameraControl
Set a command to specify scene mode  Parameter ``mode``:     Scene mode
method
setSharpness(self, value: int) -> CameraControl: CameraControl
Set a command to adjust image sharpness  Parameter ``value``:     Sharpness, range 0..4, default 1
method
method
method
method
setStrobeExternal(self, gpioNumber: int, activeLevel: int) -> CameraControl: CameraControl
Enable STROBE output driven by a MyriadX GPIO, optionally configuring the polarity This normally requires a FSIN/FSYNC/trigger input for MyriadX (usually GPIO 41), to generate timings
method
setStrobeSensor(self, activeLevel: int) -> CameraControl: CameraControl
Enable STROBE output on sensor pin, optionally configuring the polarity. Note: for many sensors the polarity is high-active and not configurable
class

depthai.CameraControl.Command

variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
method
method
method
method
method
method
method
method
method
method
property
property
class

depthai.EdgeDetectorConfigData

method
property
sobelFilterHorizontalKernel
Used for horizontal gradient computation in 3x3 Sobel filter Format - 3x3 matrix, 2nd column must be 0 Default - +1 0 -1; +2 0 -2; +1 0 -1
method
property
sobelFilterVerticalKernel
Used for vertical gradient computation in 3x3 Sobel filter Format - 3x3 matrix, 2nd row must be 0 Default - +1 +2 +1; 0 0 0; -1 -2 -1
method
class

depthai.EdgeDetectorConfig(depthai.Buffer)

method
method
method
getConfigData(self) -> EdgeDetectorConfigData: EdgeDetectorConfigData
Retrieve configuration data for EdgeDetector  Returns:     EdgeDetectorConfigData: sobel filter horizontal and vertical 3x3 kernels
method
setSobelFilterKernels(self, horizontalKernel: list[list[int]], verticalKernel: list[list[int]])
Set sobel filter horizontal and vertical 3x3 kernels  Parameter ``horizontalKernel``:     Used for horizontal gradient computation in 3x3 Sobel filter  Parameter ``verticalKernel``:     Used for vertical gradient computation in 3x3 Sobel filter
class

depthai.FeatureTrackerConfig(depthai.Buffer)

class
CornerDetector
Corner detector configuration structure.
class
MotionEstimator
Used for feature reidentification between current and previous features.
class
FeatureMaintainer
FeatureMaintainer configuration structure.
method
method
method
method
method
setHwMotionEstimation(self) -> FeatureTrackerConfig: FeatureTrackerConfig
Set hardware accelerated motion estimation using block matching. Faster than optical flow (software implementation) but might not be as accurate.
method
method
setNumTargetFeatures(self, numTargetFeatures: int) -> FeatureTrackerConfig: FeatureTrackerConfig
Set number of target features to detect.  Parameter ``numTargetFeatures``:     Number of features
method
class

depthai.FeatureTrackerConfig.CornerDetector

class
Type
Members:    HARRIS    SHI_THOMASI
class
Thresholds
Threshold settings structure for corner detector.
method
property
cellGridDimension
Ensures distributed feature detection across the image. Image is divided into horizontal and vertical cells, each cell has a target feature count = numTargetFeatures / cellGridDimension. Each cell has its own feature threshold. A value of 4 means that the image is divided into 4x4 cells of equal width/height. Maximum 4, minimum 1.
method
property
enableSobel
Enable 3x3 Sobel operator to smoothen the image whose gradient is to be computed. If disabled, a simple 1D row/column differentiator is used for gradient.
method
property
enableSorting
Enable sorting detected features based on their score or not.
method
property
numMaxFeatures
Hard limit for the maximum number of features that can be detected. 0 means auto, will be set to the maximum value based on memory constraints.
method
property
numTargetFeatures
Target number of features to detect. Maximum number of features is determined at runtime based on algorithm type.
method
property
thresholds
Threshold settings. These are advanced settings, suitable for debugging/special cases.
method
property
type
Corner detector algorithm type.
method
class

depthai.FeatureTrackerConfig.CornerDetector.Thresholds

method
property
decreaseFactor
When detected number of features exceeds the maximum in a cell threshold is lowered by multiplying its value with this factor.
method
property
increaseFactor
When detected number of features doesn't exceed the maximum in a cell, threshold is increased by multiplying its value with this factor.
method
property
initialValue
Minimum strength of a feature which will be detected. 0 means automatic threshold update. Recommended so the tracker can adapt to different scenes/textures. Each cell has its own threshold. Empirical value.
method
property
max
Maximum limit for threshold. Applicable when automatic threshold update is enabled. 0 means auto. Empirical value.
method
property
min
Minimum limit for threshold. Applicable when automatic threshold update is enabled. 0 means auto, 6000000 for HARRIS, 1200 for SHI_THOMASI. Empirical value.
method
class

depthai.FeatureTrackerConfig.MotionEstimator

class
Type
Members:    LUCAS_KANADE_OPTICAL_FLOW    HW_MOTION_ESTIMATION
class
OpticalFlow
Optical flow configuration structure.
method
property
enable
Enable motion estimation or not.
method
property
opticalFlow
Optical flow configuration. Takes effect only if MotionEstimator algorithm type set to LUCAS_KANADE_OPTICAL_FLOW.
method
property
type
Motion estimator algorithm type.
method
class

depthai.FeatureTrackerConfig.MotionEstimator.OpticalFlow

method
property
epsilon
Feature tracking termination criteria. Optical flow will refine the feature position on each pyramid level until the displacement between two refinements is smaller than this value. Decreasing this number increases runtime.
method
property
maxIterations
Feature tracking termination criteria. Optical flow will refine the feature position maximum this many times on each pyramid level. If the Epsilon criteria described in the previous chapter is not met after this number of iterations, the algorithm will continue with the current calculated value. Increasing this number increases runtime.
method
property
pyramidLevels
Number of pyramid levels, only for optical flow. AUTO means it's decided based on input resolution: 3 if image width <= 640, else 4. Valid values are either 3/4 for VGA, 4 for 720p and above.
method
property
searchWindowHeight
Image patch height used to track features. Must be an odd number, maximum 9. N means the algorithm will be able to track motion at most (N-1)/2 pixels in a direction per pyramid level. Increasing this number increases runtime
method
property
searchWindowWidth
Image patch width used to track features. Must be an odd number, maximum 9. N means the algorithm will be able to track motion at most (N-1)/2 pixels in a direction per pyramid level. Increasing this number increases runtime
method
class

depthai.FeatureTrackerConfig.FeatureMaintainer

method
property
enable
Enable feature maintaining or not.
method
property
lostFeatureErrorThreshold
Optical flow measures the tracking error for every feature. If the point can’t be tracked or it’s out of the image it will set this error to a maximum value. This threshold defines the level where the tracking accuracy is considered too bad to keep the point.
method
property
minimumDistanceBetweenFeatures
Used to filter out detected feature points that are too close. Requires sorting enabled in detector. Unit of measurement is squared euclidean distance in pixels.
method
property
trackedFeatureThreshold
Once a feature was detected and we started tracking it, we need to update its Harris score on each image. This is needed because a feature point can disappear, or it can become too weak to be tracked. This threshold defines the point where such a feature must be dropped. As the goal of the algorithm is to provide longer tracks, we try to add strong points and track them until they are absolutely untrackable. This is why, this value is usually smaller than the detection threshold.
method
class

depthai.ThermalConfig(depthai.Buffer)

method
method
property
ambientParams
Ambient factors that affect the temperature measurement of a Thermal sensor.
method
property
ffcParams
Parameters for Flat-Field-Correction.
method
property
imageParams
Image signal processing parameters on the sensor.
method
class

depthai.ThermalImageParams

method
property
brightnessLevel
Image brightness level, 0-255.
method
property
contrastLevel
Image contrast level, 0-255.
method
property
digitalDetailEnhanceLevel
0-4 Digital etail enhance level.
method
property
orientation
Orientation of the image. Computed on the sensor.
method
property
spatialNoiseFilterLevel
0-3. Spatial noise filter level.
method
property
timeNoiseFilterLevel
0-3. Time noise filter level. Filters out the noise that appears over time.
method
class

depthai.ThermalFFCParams

variable
variable
method
property
autoFFC
Auto Flat-Field-Correction. Controls wheather the shutter is controlled by the sensor module automatically or not.
method
property
autoFFCTempThreshold
Auto FFC trigger threshold. The condition for triggering the auto FFC is that the change of Vtemp value exceeds a certain threshold, which is called the Auto FFC trigger threshold.
method
property
closeManualShutter
Set this to True/False to close/open the shutter when autoFFC is disabled.
method
property
fallProtection
The shutter blade may open/close abnormally during strong mechanical shock (such as fall), and a monitoring process is designed in the firmware to correct the abnormal shutter switch in time. Turn on or off the fall protect mechanism.
method
property
maxFFCInterval
Maximum FFC interval when auto FFC is enabled. The time interval between two FFC should not be more than this value.
method
property
minFFCInterval
Minimum FFC interval when auto FFC is enabled. The time interval between two FFC should not be less than this value.
method
property
minShutterInterval
Frequent FFC will cause shutter heating, resulting in abnormal FFC effect and abnormal temperature measurement. Regardless of which mechanism triggers FFC, the minimum trigger interval must be limited.
method
class

depthai.ThermalAmbientParams

method
property
atmosphericTemperature
Atmospheric temperature. unit:K, range:230-500(high gain), 230-900(low gain)
method
property
atmosphericTransmittance
Atmospheric transmittance. unit:1/128, range:1-128(0.01-1)
method
property
distance
Distance to the measured object. unit:cnt(128cnt=1m), range:0-25600(0-200m)
method
property
gainMode
Gain mode, low or high.
method
property
reflectionTemperature
Reflection temperature. unit:K, range:230-500(high gain), 230-900(low gain)
method
property
targetEmissivity
Emissivity. unit:1/128, range:1-128(0.01-1)
method
class

depthai.ImageManipConfig(depthai.Buffer)

class
ResizeMode
Members:    NONE    LETTERBOX    CENTER_CROP    STRETCH
method
method
method
method
addCropRotatedRect(self, rect: RotatedRect, normalizedCoords: bool) -> ImageManipConfig: ImageManipConfig
Crops the image to the specified (rotated) rectangle  Parameter ``rect``:     RotatedRect to crop  Parameter ``normalizedCoords``:     If true, the coordinates are normalized to range [0, 1] where 1 maps to the     width/height of the image
method
method
method
method
method
addTransformAffine(self, mat: typing.Annotated[list[float], pybind11_stubgen.typing_ext.FixedSize(4)]) -> ImageManipConfig: ImageManipConfig
Applies an affine transformation to the image  Parameter ``matrix``:     an array containing a 2x2 matrix representing the affine transformation
method
addTransformFourPoints(self, src: typing.Annotated[list[Point2f], pybind11_stubgen.typing_ext.FixedSize(4)], dst: typing.Annotated[list[Point2f], pybind11_stubgen.typing_ext.FixedSize(4)], normalizedCoords: bool) -> ImageManipConfig: ImageManipConfig
Applies a perspective transformation to the image  Parameter ``src``:     Source points  Parameter ``dst``:     Destination points  Parameter ``normalizedCoords``:     If true, the coordinates are normalized to range [0, 1] where 1 maps to the     width/height of the image
method
addTransformPerspective(self, mat: typing.Annotated[list[float], pybind11_stubgen.typing_ext.FixedSize(9)]) -> ImageManipConfig: ImageManipConfig
Applies a perspective transformation to the image  Parameter ``matrix``:     an array containing a 3x3 matrix representing the perspective transformation
method
clearOps(self) -> ImageManipConfig: ImageManipConfig
Removes all operations from the list (does not affect output configuration)
method
getUndistort(self) -> bool: bool
Gets the undistort flag  Returns:     True if undistort is enabled, false otherwise
method
method
method
setFrameType(self, type: ImgFrame.Type) -> ImageManipConfig: ImageManipConfig
Sets the frame type of the output image  Parameter ``frameType``:     Frame type of the output image
method
setOutputCenter(self, c: bool) -> ImageManipConfig: ImageManipConfig
Centers the content in the output image without resizing  Parameter ``c``:     True to center the content, false otherwise
method
setOutputSize(self, w: int, h: int, mode: ImageManipConfig.ResizeMode = ...) -> ImageManipConfig: ImageManipConfig
Sets the output size of the image  Parameter ``w``:     Width of the output image  Parameter ``h``:     Height of the output image  Parameter ``mode``:     Resize mode. NONE - no resize, STRETCH - stretch to fit, LETTERBOX - keep     aspect ratio and pad with background color, CENTER_CROP - keep aspect ratio     and crop
method
setReusePreviousImage(self, reuse: bool) -> ImageManipConfig: ImageManipConfig
Instruct ImageManip to not remove current image from its queue and use the same for next message.  Parameter ``reuse``:     True to enable reuse, false otherwise
method
setSkipCurrentImage(self, skip: bool) -> ImageManipConfig: ImageManipConfig
Instructs ImageManip to skip current image and wait for next in queue.  Parameter ``skip``:     True to skip current image, false otherwise
method
class

depthai.ImgDetections(depthai.Buffer, depthai.ProtoSerializable, depthai.Transformable)

variable
variable
variable
method
method
method
getCvSegmentationMask(self) -> numpy.ndarray|None: numpy.ndarray|None
Retrieves mask data as a cv::Mat copy with specified width and height. If mask data is not set, returns std::nullopt.  Parameter ``allocator``:     Allows callers to supply a custom cv::MatAllocator for zero-copy/custom     memory management; nullptr uses OpenCV’s default.
method
getCvSegmentationMaskByClass(self, semantic_class: int) -> numpy.ndarray|None: numpy.ndarray|None
Retrieves data by the semantic class. If no mask data is not set, returns std::nullopt.  Parameter ``semanticClass``:     Semantic class index  Parameter ``allocator``:     Allows callers to supply a custom cv::MatAllocator for zero-copy/custom     memory management; nullptr uses OpenCV’s default.
method
getCvSegmentationMaskByIndex(self, index: int) -> numpy.ndarray|None: numpy.ndarray|None
Returns a binary mask where pixels belonging to the instance index are set to 1, others to 0. If mask data is not set, returns std::nullopt.  Parameter ``index``:     Instance index  Parameter ``allocator``:     Allows callers to supply a custom cv::MatAllocator for zero-copy/custom     memory management; nullptr uses OpenCV’s default.
method
getMaskData(self) -> typing.Any: typing.Any
Returns a copy of the segmentation mask data as a vector of bytes. If mask data is not set, returns std::nullopt.
method
getSegmentationMask(self) -> ImgFrame|None: ImgFrame|None
Returns the segmentation mask as an ImgFrame. If mask data is not set, returns std::nullopt.
method
getSegmentationMaskHeight(self) -> int: int
Returns the height of the segmentation mask.
method
getSegmentationMaskWidth(self) -> int: int
Returns the width of the segmentation mask.
method
method
setCvSegmentationMask(self, mask: numpy.ndarray)
Copies cv::Mat data to Segmentation Mask buffer  Parameter ``frame``:     Input cv::Mat frame from which to copy the data @note Throws if mask is not     a single channel INT8 type.
method
setSegmentationMask(self, frame: ImgFrame)
Sets the segmentation mask from a vector of bytes. The size of the vector must be equal to width * height.
method
setTransformation(self, transformation: ImgTransformation|None)
Specifies image transformation data  Parameter ``transformation``:     transformation data
method
transformTo(self, target: ImgTransformation) -> ImgDetections: ImgDetections
Returns a new ImgDetections message with the detections transformed into the target image transformation.  If the target transformation has a different source coordinate system (eg. different camera socket) than the one the detections were originally generated in, the remapping will be inaccurate due to the lack of depth information.  The segmentation mask is not transformed. Use Align node to transform the segmentation mask to the target transformation if needed.  Parameter ``target``:     Target image transformation.
class

depthai.ImgDetection

variable
variable
variable
variable
variable
variable
variable
method
method
method
method
method
method
method
method
method
getKeypoints(self) -> list[Keypoint]: list[Keypoint]
Returns a list of Keypoint objects, or empty list if no keypoints were set.
method
getKeypoints2f(self) -> VectorPoint2f: VectorPoint2f
Returns a list of Point2f coordinates of the keypoints, or empty list if no keypoints were set.
method
getKeypoints3f(self) -> list[Point3f]: list[Point3f]
Returns a list of Point3f coordinates of the keypoints, or empty list if no keypoints were set.
method
method
method
method
method
method
method
transform(self, source: ImgTransformation, target: ImgTransformation)
Transforms the detection from the source ImgTransformation to the target ImgTransformation.  Parameter ``source``:     Source image transformation.  Parameter ``target``:     Target image transformation.
class

depthai.ImgFrame(depthai.Buffer, depthai.ProtoSerializable)

class
Type
Members:    YUV422i    YUV444p    YUV420p    YUV422p    YUV400p    RGBA8888    RGB161616    RGB888p    BGR888p    RGB888i    BGR888i    RGBF16F16F16p    BGRF16F16F16p    RGBF16F16F16i    BGRF16F16F16i    GRAY8    GRAYF16    LUT2    LUT4    LUT16    RAW16    RAW14    RAW12    RAW10    RAW8    PACK10    PACK12    YUV444i    NV12    NV21    BITSTREAM    HDR    RAW32    NONE
class
Fsync
Members:    NONE    INPUT    OUTPUT    PTP
class
method
method
method
getBytesPerPixel(self) -> float: float
Retrieves image bytes per pixel
method
getCategory(self) -> int: int
Retrieves image category
method
getColorTemperature(self) -> int: int
Retrieves white-balance color temperature of the light source, in kelvins
method
getCvFrame(self) -> numpy.ndarray: numpy.ndarray
@note This API only available if OpenCV support is enabled  Retrieves cv::Mat suitable for use in common opencv functions. ImgFrame is converted to color BGR interleaved or grayscale depending on type.  A copy is always made  Returns:     cv::Mat for use in opencv functions
method
method
getFps(self) -> float: float
Retrieves sensor FPS for this frame.
method
getFrame(self) -> numpy.ndarray: numpy.ndarray
@note This API only available if OpenCV support is enabled  Retrieves data as cv::Mat with specified width, height and type  Parameter ``copy``:     If false only a reference to data is made, otherwise a copy  Returns:     cv::Mat with corresponding to ImgFrame parameters
method
getFsync(self) -> ImgFrame.Fsync: ImgFrame.Fsync
Retrieves effective frame sync mode for this frame.
method
getHeight(self) -> int: int
Retrieves image height in pixels
method
getInstanceNum(self) -> int: int
Retrieves instance number
method
getLensPosition(self) -> int: int
Retrieves lens position, range 0..255. Returns -1 if not available
method
getLensPositionRaw(self) -> float: float
Retrieves lens position, range 0.0f..1.0f. Returns -1 if not available
method
getPlaneHeight(self) -> int: int
Retrieves image plane height in lines
method
getPlaneStride(self, planeIndex: int) -> int: int
Retrieves image plane stride (offset to next plane) in bytes  Parameter ``current``:     plane index, 0 or 1
method
getSensitivity(self) -> int: int
Retrieves sensitivity, as an ISO value
method
getSensorMode(self) -> int: int
Retrieves selected sensor mode index for this frame.
method
getSensorTemperature(self) -> float|None: float|None
Retrieves sensor temperature in degrees Celsius. Returns an empty optional if not available.
method
getSourceDFov(self) -> float: float
@note Fov API works correctly only on rectilinear frames Get the source diagonal field of view in degrees  Returns:     field of view in degrees
method
getSourceHFov(self) -> float: float
@note Fov API works correctly only on rectilinear frames Get the source horizontal field of view  Parameter ``degrees``:     field of view in degrees
method
getSourceHeight(self) -> int: int
Retrieves source image height in pixels
method
getSourceVFov(self) -> float: float
@note Fov API works correctly only on rectilinear frames Get the source vertical field of view  Parameter ``degrees``:     field of view in degrees
method
getSourceWidth(self) -> int: int
Retrieves source image width in pixels
method
getStride(self) -> int: int
Retrieves image line stride in bytes
method
method
method
method
method
method
getWidth(self) -> int: int
Retrieves image width in pixels
method
setCategory(self, category: int) -> ImgFrame: ImgFrame
Parameter ``category``:     Image category
method
setCvFrame(self, array: numpy.ndarray, type: ImgFrame.Type) -> ImgFrame: ImgFrame
@note This API only available if OpenCV support is enabled  Copies cv::Mat data to the ImgFrame buffer and converts to a specific type.  Parameter ``frame``:     Input cv::Mat BGR frame or single channel frame from which to copy the data     from.  Parameter ``type``:     Specifies the target image format for the internal buffer, including color     space, layout, and bit depth.
method
setFrame(self, array: numpy.ndarray) -> ImgFrame: ImgFrame
@note This API only available if OpenCV support is enabled  Copies cv::Mat data to ImgFrame buffer  Parameter ``frame``:     Input cv::Mat frame from which to copy the data
method
setHeight(self, height: int) -> ImgFrame: ImgFrame
Specifies frame height  Parameter ``height``:     frame height
method
setInstanceNum(self, instance: int) -> ImgFrame: ImgFrame
Instance number relates to the origin of the frame (which camera)  Parameter ``instance``:     Instance number
method
method
setStride(self, stride: int) -> ImgFrame: ImgFrame
Specifies frame stride  Parameter ``stride``:     frame stride
method
setTransformation(self, transformation: ImgTransformation) -> ImgFrame: ImgFrame
Specifies image transformation data  Parameter ``transformation``:     transformation data
method
setType(self, type: ImgFrame.Type) -> ImgFrame: ImgFrame
Specifies frame type, RGB, BGR, ...  Parameter ``type``:     Type of image
method
setWidth(self, width: int) -> ImgFrame: ImgFrame
Specifies frame width  Parameter ``width``:     frame width
method
validateTransformations(self) -> bool: bool
Check that the image transformation match the image size  Returns:     true if the transformations are valid
class

depthai.ImgFrame.Type

variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
method
method
method
method
method
method
method
method
method
method
property
property
class

depthai.ImgFrame.Specs

class

depthai.ImgTransformation

method
method
method
addCrop(self, x: int, y: int, width: int, height: int) -> ImgTransformation: ImgTransformation
Add a crop transformation.  Parameter ``x``:     X coordinate of the top-left corner of the crop  Parameter ``y``:     Y coordinate of the top-left corner of the crop  Parameter ``width``:     Width of the crop  Parameter ``height``:     Height of the crop
method
method
method
addPadding(self, x: int, y: int, width: int, height: int) -> ImgTransformation: ImgTransformation
Add a pad transformation. Works like crop, but in reverse.  Parameter ``top``:     Padding on the top  Parameter ``bottom``:     Padding on the bottom  Parameter ``left``:     Padding on the left  Parameter ``right``:     Padding on the right
method
addRotation(self, angle: float, rotationPoint: Point2f) -> ImgTransformation: ImgTransformation
Add a rotation transformation.  Parameter ``angle``:     Angle in degrees  Parameter ``rotationPoint``:     Point around which to rotate
method
addScale(self, scaleX: float, scaleY: float) -> ImgTransformation: ImgTransformation
Add a scale transformation.  Parameter ``scaleX``:     Scale factor in the horizontal direction  Parameter ``scaleY``:     Scale factor in the vertical direction
method
method
method
method
getDistortionCoefficients(self) -> list[float]: list[float]
Retrieve the distortion coefficients of the source sensor  Returns:     vector of distortion coefficients
method
getDistortionModel(self) -> CameraModel: CameraModel
Retrieve the distortion model of the source sensor  Returns:     Distortion model
method
getDstMaskPt(self, x: int, y: int) -> bool: bool
Returns true if the point is inside the image region (not in the background region).
method
getExtrinsics(self) -> Extrinsics: Extrinsics
Retrieve the pose of the source sensor or virtual camera relative to its target coordinate system. The target coordinate system is identified by Extrinsics::toDeviceId and Extrinsics::toCameraSocket.  Returns:     Extrinsics
method
getExtrinsicsTransformationMatrixTo(self, to: ImgTransformation, useSpecTranslation: bool = False, sourceUnit: LengthUnit = ...) -> typing.Annotated[list[typing.Annotated[list[float], pybind11_stubgen.typing_ext.FixedSize(4)]], pybind11_stubgen.typing_ext.FixedSize(4)]: typing.Annotated[list[typing.Annotated[list[float], pybind11_stubgen.typing_ext.FixedSize(4)]], pybind11_stubgen.typing_ext.FixedSize(4)]
Get the extrinsic transformation matrix from the source coordinate system of this transformation to the target coordinate system of the to transformation.  Parameter ``to``:     Target transformation to get extrinsics to  Parameter ``useSpecTranslation``:     If true, the translation vector w.r.t. the CAD design will be used instead     of the translation vector obtained through calibration.  Parameter ``sourceUnit``:     The desired measurement unit in which to return the transformation matrix     in.  Returns:     4x4 homogeneous transformation matrix representing the extrinsics from this     transformation to the target transformation @note Both transformations must     have a compatible target device ID and a common target camera socket.     Otherwise extrinsics cannot be calculated.
method
method
method
method
method
method
getSize(self) -> tuple[int, int]: tuple[int, int]
Retrieve the size of the frame. Should be equal to the size of the corresponding ImgFrame message.  Returns:     Size of the frame
method
method
method
getSourceSize(self) -> tuple[int, int]: tuple[int, int]
Retrieve the size of the source frame from which this frame was derived.  Returns:     Size of the frame
method
method
getSrcMaskPt(self, x: int, y: int) -> bool: bool
Returns true if the point is inside the transformed region of interest (determined by crops used).
method
method
method
method
invTransformPoint(self, point: Point2f) -> Point2f: Point2f
Transform a point from the current frame to the source frame.  Parameter ``point``:     Point to transform  Returns:     Transformed point
method
invTransformRect(self, rect: RotatedRect) -> RotatedRect: RotatedRect
Transform a rotated rect from the current frame to the source frame.  Parameter ``rect``:     Rectangle to transform  Returns:     Transformed rectangle
method
isAlignedTo(self, to: ImgTransformation) -> bool: bool
Check if the transformations are aligned  Parameter ``to``:     Transformation to compare with
method
isEqualTransformation(self, other: ImgTransformation) -> bool: bool
Two transformations are equal if the transformation matrices, intrinsic matrices, distortion models, distortion coefficients, extrinsics, and sizes are all equal.  Parameter ``other``:     Transformation to compare with  Returns:     True if the transformations are equal, false otherwise
method
isValid(self) -> bool: bool
Check if the transformations are valid. The transformations are valid if the source frame size and the current frame size are set.
method
project3DPoint(self, point: Point3f) -> Point2f: Point2f
Project a 3D spatial point into 2D point in the current frame defined by this transformation.  Parameter ``point``:     3D point to project  Returns:     Projected 2D point in the current frame @note This function assumes that the     point is in the coordinate system of the current frame.
method
project3DPointFrom(self, from_: ImgTransformation, point: Point3f) -> Point2f: Point2f
Project a 3D point from the source frame (from transformation) into a 2D point in the current frame (this transformation).  Parameter ``from``:     Transformation to project from  Parameter ``point3f``:     3D point to project  Returns:     Projected 2D point in the current frame @note This function assumes that the     point3f is in the coordinate system of the source frame.
method
project3DPointTo(self, to: ImgTransformation, point: Point3f) -> Point2f: Point2f
Project a 3D spatial point from the source coordinate system (this transformation) into a 2D point in the target frame (to transformation).  Parameter ``to``:     Target transformation to project to  Parameter ``point3f``:     3D point to project  Returns:     Projected 2D point in the target frame (to transformation) @note This     function assumes that the point3f is in the coordinate system of the current     frame.
method
projectPointTo(self, to: ImgTransformation, point: Point2f, depth: float) -> Point2f: Point2f
Project a 2D point from the source frame defined by this transformation into a 2D point in the target frame defined by the to transformation. This function will use the depth of the point to project it into 3D space and then reproject it back to 2D in the target frame.  Parameter ``to``:     Target transformation to project to  Parameter ``point2f``:     Source 2D point in the current frame  Parameter ``depth``:     (mm) Depth of the point to project  Returns:     Projected 2D point in the target frame (to transformation)
method
rebaseExtrinsics(self, localOriginToTarget: Extrinsics) -> ImgTransformation: ImgTransformation
Re-express the source extrinsics relative to a new target coordinate system.  The supplied transform must map the current local calibration origin to the new target. Only the extrinsics are changed; all image-space transformation data is preserved. The rebased extrinsics translation is stored in centimeters.  Parameter ``localOriginToTarget``:     Transform from the current local calibration origin to the new target     coordinate system.  Returns:     This transformation.
method
remap3DPointFrom(self, from_: ImgTransformation, point: Point3f) -> Point3f: Point3f
Remap a 3D point to the coordinate system of this transformation from the source coordinate system of the from transformation.  Parameter ``from``:     Transformation to remap from  Parameter ``point``:     3D point to remap  Returns:     Remapped 3D point in the current coordinate system @note This function     assumes that the point is in the coordinate system of the source frame.
method
remap3DPointTo(self, to: ImgTransformation, point: Point3f) -> Point3f: Point3f
Remap a 3D point from the source coordinate system of this transformation to the coordinate system of the target transformation (to transformation).  Parameter ``to``:     Target transformation to remap to  Parameter ``point``:     3D point to remap  Returns:     Remapped 3D point in the target coordinate system @note This function     assumes that the point is in the coordinate system of the current frame.
method
remapPointFrom(self, from_: ImgTransformation, point: Point2f) -> Point2f: Point2f
Remap a point to this transformation from another. If the intrinsics are different (e.g. different camera), the function will also use the intrinsics to remap the point.  Parameter ``from``:     Transformation to remap from  Parameter ``point``:     Point to remap
method
remapPointTo(self, to: ImgTransformation, point: Point2f) -> Point2f: Point2f
Remap a point from this transformation to another. If the intrinsics are different (e.g. different camera), the function will also use the intrinsics to remap the point.  Parameter ``to``:     Transformation to remap to  Parameter ``point``:     Point to remap @note This function assumes both transformations have the     same source (eg. same source camera socket). If they don't, remapping will     be inaccurate.
method
remapRectFrom(self, from_: ImgTransformation, rect: RotatedRect) -> RotatedRect: RotatedRect
Remap a rotated rect to this transformation from another. If the intrinsics are different (e.g. different camera), the function will also use the intrinsics to remap the rect.  Parameter ``from``:     Transformation to remap from  Parameter ``rect``:     RotatedRect to remap
method
remapRectTo(self, to: ImgTransformation, rect: RotatedRect) -> RotatedRect: RotatedRect
Remap a rotated rect from this transformation to another. If the intrinsics are different (e.g. different camera), the function will also use the intrinsics to remap the rect.  Parameter ``to``:     Transformation to remap to  Parameter ``rect``:     RotatedRect to remap
method
method
method
method
method
method
method
transformPoint(self, point: Point2f) -> Point2f: Point2f
Transform a point from the source frame to the current frame.  Parameter ``point``:     Point to transform  Returns:     Transformed point
method
transformRect(self, rect: RotatedRect) -> RotatedRect: RotatedRect
Transform a rotated rect from the source frame to the current frame.  Parameter ``rect``:     Rectangle to transform  Returns:     Transformed rectangle
class

depthai.EncodedFrame(depthai.Buffer, depthai.ProtoSerializable)

class
Profile
Members:    JPEG    AVC    HEVC
class
FrameType
Members:    I    P    B    Unknown
method
method
method
getBitrate(self) -> int: int
Retrieves the encoding bitrate
method
getColorTemperature(self) -> int: int
Retrieves white-balance color temperature of the light source, in kelvins
method
method
getFps(self) -> float: float
Retrieves sensor FPS for this frame.
method
method
getFsync(self) -> ImgFrame.Fsync: ImgFrame.Fsync
Retrieves effective frame sync mode for this frame.
method
getHeight(self) -> int: int
Retrieves image height in pixels
method
getInstanceNum(self) -> int: int
Retrieves instance number
method
getLensPosition(self) -> int: int
Retrieves lens position, range 0..255. Returns -1 if not available
method
getLensPositionRaw(self) -> float: float
Retrieves lens position, range 0.0f..1.0f. Returns -1 if not available
method
getLossless(self) -> bool: bool
Returns true if encoding is lossless (JPEG only)
method
getProfile(self) -> EncodedFrame.Profile: EncodedFrame.Profile
Retrieves the encoding profile (JPEG, AVC or HEVC)
method
getQuality(self) -> int: int
Retrieves the encoding quality
method
getSensitivity(self) -> int: int
Retrieves sensitivity, as an ISO value
method
getSensorMode(self) -> int: int
Retrieves selected sensor mode index for this frame.
method
getSensorTemperature(self) -> float|None: float|None
Retrieves sensor temperature in degrees Celsius. Returns an empty optional if not available.
method
method
getWidth(self) -> int: int
Retrieves image width in pixels
method
method
method
setHeight(self, height: int) -> EncodedFrame: EncodedFrame
Specifies frame height  Parameter ``height``:     frame height
method
setLossless(self, arg0: bool) -> EncodedFrame: EncodedFrame
Returns true if encoding is lossless (JPEG only)
method
setProfile(self, arg0: EncodedFrame.Profile) -> EncodedFrame: EncodedFrame
Retrieves the encoding profile (JPEG, AVC or HEVC)
method
method
method
method
setWidth(self, width: int) -> EncodedFrame: EncodedFrame
Specifies frame width  Parameter ``width``:     frame width
class

depthai.IMUReportAccelerometer(depthai.IMUReport)

variable
variable
variable
method
class

depthai.IMUReportGyroscope(depthai.IMUReport)

variable
variable
variable
method
class

depthai.IMUReportMagneticField(depthai.IMUReport)

variable
variable
variable
method
class

depthai.IMUReportRotationVectorWAcc(depthai.IMUReport)

class

depthai.IMUData(depthai.Buffer, depthai.ProtoSerializable)

class

depthai.MessageGroup(depthai.Buffer)

method
method
method
method
method
method
getIntervalNs(self) -> int: int
Retrieves interval between the first and the last message in the group, measured with the timestamp source that produced the group.
method
getMessageNames(self) -> list[str]: list[str]
Gets the names of messages in the group
method
method
method
isSynced(self, thresholdNs: int) -> bool: bool
True if all messages in the group are in the interval  Parameter ``thresholdNs``:     Maximal interval between messages
method
setTimestampSource(self, source: SyncProperties.TimestampSource)
Set the timestamp source this group was synced with. Used by the host Sync node; groups received from a device keep the DEVICE default.
class

depthai.NNData(depthai.Buffer, depthai.ProtoSerializable)

method
method
method
method
getAllLayerNames(self) -> list[str]: list[str]
Returns:     Names of all layers added
method
getAllLayers(self) -> list[TensorInfo]: list[TensorInfo]
Returns:     All layers and their information
method
method
getLayerDatatype(self, name: str, datatype: TensorInfo.DataType) -> bool: bool
Retrieve datatype of a layers tensor  Parameter ``name``:     Name of the layer  Parameter ``datatype``:     Datatype of layers tensor  Returns:     True if layer exists, false otherwise
method
method
getTensorDatatype(self, name: str) -> TensorInfo.DataType: TensorInfo.DataType
Get the datatype of a given tensor  Returns:     TensorInfo::DataType tensor datatype
method
getTensorInfo(self, name: str) -> TensorInfo|None: TensorInfo|None
Retrieve tensor information  Parameter ``name``:     Name of the tensor  Returns:     Tensor information
method
method
hasLayer(self, name: str) -> bool: bool
Checks if given layer exists  Parameter ``name``:     Name of the layer  Returns:     True if layer exists, false otherwise
method
setTransformation(self, transformation: ImgTransformation|None)
Specifies image transformation data  Parameter ``transformation``:     transformation data
class

depthai.NeuralDepthConfig(depthai.Buffer)

class
method
method
method
getConfidenceThreshold(self) -> int: int
Get confidence threshold for disparity calculation
method
getCustomDepthUnitMultiplier(self) -> float: float
Get custom depth unit multiplier relative to 1 meter.
method
method
getEdgeThreshold(self) -> int: int
Get edge threshold for disparity calculation
method
setConfidenceThreshold(self, confidenceThreshold: int) -> NeuralDepthConfig: NeuralDepthConfig
Confidence threshold for disparity calculation  Parameter ``confThr``:     Confidence threshold value 0..255
method
method
method
setEdgeThreshold(self, edgeThreshold: int) -> NeuralDepthConfig: NeuralDepthConfig
Set edge threshold for disparity calculation  Parameter ``edgeThr``:     Edge threshold value 0..255
property
postProcessing
Controls the postprocessing of disparity and/or depth map.
method
class

depthai.NeuralDepthConfig.PostProcessing

class
TemporalFilter
Temporal filtering with optional persistence.
class
ThresholdFilter
Threshold filtering. Filters out distances outside of a given interval.
method
property
confidenceThreshold
Confidence threshold for disparity calculation, Confidences above this value will be considered valid. Valid range is [0,255].
method
property
edgeThreshold
Edge threshold for disparity calculation, Pixels with edge magnitude below this value will be considered invalid. Valid range is [0,255].
method
property
temporalFilter
Temporal filtering with optional persistence.
method
property
thresholdFilter
Threshold filtering. Filters out distances outside of a given interval.
method
class

depthai.NeuralDepthConfig.PostProcessing.TemporalFilter

class
PersistencyMode
Persistency algorithm type.  Members:    PERSISTENCY_OFF :     VALID_8_OUT_OF_8 :     VALID_2_IN_LAST_3 :     VALID_2_IN_LAST_4 :     VALID_2_OUT_OF_8 :     VALID_1_IN_LAST_2 :     VALID_1_IN_LAST_5 :     VALID_1_IN_LAST_8 :     PERSISTENCY_INDEFINITELY : 
method
method
property
alpha
The Alpha factor in an exponential moving average with Alpha=1 - no filter. Alpha = 0 - infinite filter. Determines the extent of the temporal history that should be averaged.
method
property
delta
Step-size boundary. Establishes the threshold used to preserve surfaces (edges). If the disparity value between neighboring pixels exceed the disparity threshold set by this delta parameter, then filtering will be temporarily disabled. Default value 0 means auto: 3 disparity integer levels. In case of subpixel mode it's 3*number of subpixel levels.
method
property
enable
Whether to enable or disable the filter.
method
property
persistencyMode
Persistency mode. If the current disparity/depth value is invalid, it will be replaced by an older value, based on persistency mode.
method
class

depthai.NeuralDepthConfig.PostProcessing.TemporalFilter.PersistencyMode

class

depthai.NeuralDepthConfig.PostProcessing.ThresholdFilter

method
method
property
maxRange
Maximum range in depth units. Depth values over this value are invalidated.
method
property
minRange
Minimum range in depth units. Depth values under this value are invalidated.
method
class

depthai.GPUStereoConfig(depthai.Buffer)

method
method
method
getConfidenceThreshold(self) -> int: int
Get the confidence threshold for disparity filtering.
method
setConfidenceThreshold(self, threshold: int) -> GPUStereoConfig: GPUStereoConfig
Set the confidence threshold for disparity filtering.  Pixels with a matching cost above this threshold are invalidated.  Parameter ``threshold``:     Value in range [0, 255]. 0 disables the filter. Values outside the range are     clamped.
property
confidenceThreshold
Confidence threshold for disparity filtering.  Value in range [0, 255]. 0 disables the filter.
method
class

depthai.SpatialImgDetection

variable
variable
variable
variable
variable
variable
method
method
method
getAngle(self) -> float: float
Returns the angle of the bounding box.
method
getBoundingBox(self) -> RotatedRect: RotatedRect
Returns bounding box if it was set, else it constructs a new one from the legacy xmin, ymin, xmax, ymax values.
method
getCenterX(self) -> float: float
Returns the X coordinate of the center of the bounding box.
method
getCenterY(self) -> float: float
Returns the Y coordinate of the center of the bounding box.
method
method
getHeight(self) -> float: float
Returns the height of the (rotated) bounding box.
method
getImgDetection(self) -> ImgDetection: ImgDetection
Converts SpatialImgDetection to ImgDetection by dropping spatial data.  Returns:     dai::ImgDetection object.
method
getKeypointSpatialCoordinates(self) -> list[Point3f]: list[Point3f]
Returns a list of spatial coordinates for each keypoint, or empty list if no keypoints were set.
method
getKeypoints(self) -> list[SpatialKeypoint]: list[SpatialKeypoint]
Returns a list of Keypoint objects, or empty list if no keypoints were set.
method
getWidth(self) -> float: float
Returns the width of the (rotated) bounding box.
method
setBoundingBox(self, boundingBox: RotatedRect)
Sets the bounding box and the legacy coordinates of the detection.
method
setEdges(self, edges: list[typing.Annotated[list[int], pybind11_stubgen.typing_ext.FixedSize(2)]])
Sets edges for the keypoints, throws if no keypoints were set beforehand.
method
method
setOuterBoundingBox(self, xmin: float, ymin: float, xmax: float, ymax: float)
Sets the bounding box and the legacy coordinates of the detection from the top- left and bottom-right points.
method
setSpatialCoordinate(self, spatialCoordinates: Point3f)
Sets spatial coordinates for the detection.  Parameter ``spatialCoordinates``:     list of Point3f objects to set. @note The size of spatialCoordinates.
property
xmax
Deprecation warning: use boundingBox instead
method
property
xmin
Deprecation warning: use boundingBox instead
method
property
ymax
Deprecation warning: use boundingBox instead
method
property
ymin
Deprecation warning: use boundingBox instead
method
class

depthai.SpatialImgDetections(depthai.Buffer, depthai.ProtoSerializable, depthai.Transformable)

variable
method
method
method
getCvSegmentationMask(self) -> numpy.ndarray|None: numpy.ndarray|None
Retrieves mask data as a cv::Mat copy with specified width and height. If mask data is not set, returns std::nullopt.  Parameter ``allocator``:     Allows callers to supply a custom cv::MatAllocator for zero-copy/custom     memory management; nullptr uses OpenCV’s default.
method
getCvSegmentationMaskByClass(self, semantic_class: int) -> numpy.ndarray|None: numpy.ndarray|None
Retrieves data by the semantic class. If no mask data is not set, returns std::nullopt.  Parameter ``semanticClass``:     Semantic class index  Parameter ``allocator``:     Allows callers to supply a custom cv::MatAllocator for zero-copy/custom     memory management; nullptr uses OpenCV’s default.
method
getCvSegmentationMaskByIndex(self, index: int) -> numpy.ndarray|None: numpy.ndarray|None
Returns a binary mask where pixels belonging to the instance index are set to 1, others to 0. If mask data is not set, returns std::nullopt.  Parameter ``index``:     Instance index  Parameter ``allocator``:     Allows callers to supply a custom cv::MatAllocator for zero-copy/custom     memory management; nullptr uses OpenCV’s default.
method
getMaskData(self) -> typing.Any: typing.Any
Returns a copy of the segmentation mask data as a vector of bytes. If mask data is not set, returns std::nullopt.
method
getSegmentationMask(self) -> ImgFrame|None: ImgFrame|None
Returns the segmentation mask as an ImgFrame. If mask data is not set, returns std::nullopt.
method
getSegmentationMaskHeight(self) -> int: int
Returns the height of the segmentation mask.
method
getSegmentationMaskWidth(self) -> int: int
Returns the width of the segmentation mask.
method
method
setCvSegmentationMask(self, mask: numpy.ndarray)
Copies cv::Mat data to Segmentation Mask buffer  Parameter ``frame``:     Input cv::Mat frame from which to copy the data @note Throws if mask is not     a single channel INT8 type.
method
setSegmentationMask(self, frame: ImgFrame)
Sets the segmentation mask from a vector of bytes. The size of the vector must be equal to width * height.
method
method
transformTo(self, target: ImgTransformation) -> SpatialImgDetections: SpatialImgDetections
Returns a new SpatialImgDetections message with the spatial detections transformed into the target image transformation.  For each detection, the bounding box is assumed to lie on a plane parallel to the image plane at depth `detection.spatialCoordinates.z` (that is, all four bounding-box corners are projected using the same depth value). The transformed corners are then fit with the smallest enclosing rotated rectangle to preserve rectangularity.  Parameter ``target``:     Target image transformation.  Returns:     SpatialImgDetections with transformed detections.
property
unit
Length unit used by all imgDetections' `spatialCoordinates` in this list.
method
class

depthai.DetectionParserConfig(depthai.Buffer)

method
method
method
getConfidenceThreshold(self) -> float: float
Get the minimum detection confidence.
method
getIouThreshold(self) -> float: float
Get the IoU threshold for non-maximum suppression.
method
setConfidenceThreshold(self, threshold: float)
Set the minimum detection confidence.
method
setIouThreshold(self, threshold: float)
Set the IoU threshold for non-maximum suppression.
property
confidenceThreshold
Minimum detection confidence. Default matches DetectionParser's startup threshold.
method
property
iouThreshold
IoU threshold for YOLO non-maximum suppression. Not used by Mobilenet-SSD or end-to-end YOLO models.
method
class

depthai.SegmentationParserConfig(depthai.Buffer)

variable
variable
method
method
method
method
getStepSize(self) -> int: int
Gets the step size for segmentation parsing.
method
setConfidenceThreshold(self, threshold: float)
Add a confidence threshold to the argmax operation over the segmentation tensor. Pixels with confidence values below this threshold will be assigned the background class (255).  Parameter ``threshold``:     Confidence threshold for segmentation parsing @note Default is -1.0f, which     means no thresholding is applied. @note Only applicable if output classes     are not in a single layer (eg. classesInOneLayer = false).
method
setStepSize(self, stepSize: int)
Sets the step size for segmentation parsing. A step size of 1 means every pixel is processed, a step size of 2 means every second pixel is processed, and so on. This can be used to speed up processing at the cost of lower resolution masks.  Parameter ``stepSize``:     Step size for segmentation parsing
class

depthai.SegmentationMask(depthai.Buffer, depthai.ProtoSerializable, depthai.Transformable)

method
method
method
getArea(self, index: int) -> int|None: int|None
Returns the area (number of pixels) of the specified instance/class index in the segmentation mask.  Parameter ``index``:     Instance/Class index @note If index is not present in the mask, returns     std::nullopt.
method
getBoundingBoxes(self, index: int, calculateRotation: bool = False) -> list[RotatedRect]: list[RotatedRect]
Returns a bounding box for each continuous region with the specified index.  Parameter ``index``:     class index  Parameter ``calculateRotation``:     If true, returns rotated bounding boxes, otherwise returns the outer, axis-     aligned bounding boxes.
method
getCentroid(self, index: int) -> Point2f|None: Point2f|None
Returns the normalized centroid (x,y) coordinates of the specified instance/class index in the segmentation mask.  Parameter ``index``:     Instance/Class index @note If index is not present in the mask, returns     std::nullopt.
method
getContour(self, index: int) -> list[VectorPoint2f]: list[VectorPoint2f]
Calls the opencv findContours function and filters the results based on the provided index. Returns filtered contour as a vector of vectors of non- normalized points. If mask data is not set, returns an empty vector.  Parameter ``index``:     class index
method
getCvMask(self) -> numpy.ndarray: numpy.ndarray
Retrieves mask data as a cv::Mat copy with specified width and height. If mask data is not set, returns an empty matrix.  Parameter ``allocator``:     Allows callers to supply a custom cv::MatAllocator for zero-copy/custom     memory management; nullptr uses OpenCV’s default.
method
getCvMaskByIndex(self, index: int) -> numpy.ndarray: numpy.ndarray
Returns a binary mask where pixels belonging to the instance index are set to 1, others to 0. If mask data is not set, returns an empty matrix.  Parameter ``index``:     Instance index  Parameter ``allocator``:     Allows callers to supply a custom cv::MatAllocator for zero-copy/custom     memory management; nullptr uses OpenCV’s default.
method
getFrame(self) -> ImgFrame: ImgFrame
Returns the segmentation mask as an ImgFrame. If mask data is not set, returns an empty frame with only metadata set.
method
getHeight(self) -> int: int
Returns the height of the segmentation mask.
method
getLabels(self) -> list[str]: list[str]
Returns all class labels associated with the segmentation mask. If no labels are set, returns an empty vector.
method
getMaskByIndex(self, index: int) -> numpy.ndarray[numpy.uint8]: numpy.ndarray[numpy.uint8]
Returns a binary mask where pixels belonging to the specified instance/class index are set to 1, others to 0. If mask data is not set, returns an empty vector.
method
getMaskByLabel(self, label: str) -> numpy.ndarray[numpy.uint8]: numpy.ndarray[numpy.uint8]
Returns a binary mask where pixels belonging to the specified class label are set to 1, others to 0. If labels are not set or label not found, returns an empty vector.
method
getMaskData(self) -> numpy.ndarray[numpy.uint8]: numpy.ndarray[numpy.uint8]
Returns a copy of the segmentation mask data as a vector of bytes. If mask data is not set, returns an empty vector.
method
method
method
getWidth(self) -> int: int
Returns the width of the segmentation mask.
method
hasValidMask(self) -> bool: bool
Returns true if the mask data is not empty and has valid size (width * height).
method
setCvMask(self, mask: numpy.ndarray)
Copies cv::Mat data to Segmentation Mask buffer  Parameter ``frame``:     Input cv::Mat frame from which to copy the data @note Throws if mask is not     a single channel INT8 type.
method
setLabels(self, labels: list[str])
Sets the class labels associated with the segmentation mask. The label at index `i` in the `labels` vector corresponds to the value `i` in the segmentation mask data array.  Parameter ``labels``:     Vector of class labels
method
method
setTransformation(self, transformation: ImgTransformation)
Specifies image transformation data  Parameter ``transformation``:     transformation data
method
transformTo(self, target: ImgTransformation) -> SegmentationMask: SegmentationMask
Returns a copy of this segmentation mask.  Segmentation mask remapping is not implemented. For optimal performance, segmentation masks should be generated from already aligned source messages instead of being transformed after the fact. Use Align on the source inputs to align segmentation masks.  Parameter ``target``:     Target image transformation.
class

depthai.SpatialLocationCalculatorConfigThresholds

class

depthai.SpatialLocationCalculatorConfigData

method
property
calculationAlgorithm
Calculation method used to obtain spatial locations Average/mean: the average of ROI is used for calculation. Min: the minimum value inside ROI is used for calculation. Max: the maximum value inside ROI is used for calculation. Mode: the most frequent value inside ROI is used for calculation. Median: the median value inside ROI is used for calculation. Default: median.
method
property
depthThresholds
Upper and lower thresholds for depth values to take into consideration.
method
property
roi
Region of interest for spatial location calculation.
method
class

depthai.SpatialLocationCalculatorConfig(depthai.Buffer)

variable
variable
variable
variable
variable
method
method
method
addROI(self, ROI: SpatialLocationCalculatorConfigData)
Add a new region of interest (ROI) to configuration data.  Parameter ``roi``:     Configuration parameters for ROI
method
getBoundingBoxScaleFactor(self) -> float: float
Retrieve scale factor for bounding boxes used in spatial calculations.
method
getCalculateSpatialKeypoints(self) -> bool: bool
Retrieve whether keypoints are used for spatial location calculation. $.. warning::  Only applicable to ImgDetections with keypoints.
method
method
getConfigData(self) -> list[SpatialLocationCalculatorConfigData]: list[SpatialLocationCalculatorConfigData]
Retrieve configuration data for SpatialLocationCalculator  Returns:     Vector of configuration parameters for ROIs (region of interests)
method
method
getKeypointRadius(self) -> int: int
Retrieve radius around keypoints used to calculate spatial coordinates.
method
getSegmentationPassthrough(self) -> bool: bool
Retrieve whether segmentation is passed through along with spatial detections. $.. warning::  Only applicable to ImgDetections with segmentation masks.
method
method
getUseSegmentation(self) -> bool: bool
Retrieve whether segmentation is used for spatial location calculation. $.. warning::  Only applicable to ImgDetections with segmentation masks.
method
setBoundingBoxScaleFactor(self, arg0: float)
Set scale factor for bounding boxes used in spatial calculations.  Parameter ``scaleFactor``:     Scale factor must be in the interval (0,1].
method
setCalculateSpatialKeypoints(self, arg0: bool)
If false, spatial coordinates of keypoints will not be calculated.  Parameter ``calculateSpatialKeypoints``:     $.. warning::  Only applicable to ImgDetections with keypoints.
method
setCalculationAlgorithm(self, arg0: SpatialLocationCalculatorAlgorithm)
Set spatial location calculation algorithm. Possible values:  - MEDIAN: Median of all depth values in the ROI - AVERAGE: Average of all depth values in the ROI - MIN: Minimum depth value in the ROI - MAX: Maximum depth value in the ROI - MODE: Most frequent depth value in the ROI
method
setDepthThresholds(self, arg0: int, arg1: int)
Set the lower and upper depth value thresholds to be used in the spatial calculations.  Parameter ``lowerThreshold``:     Lower threshold in depth units (millimeter by default).  Parameter ``upperThreshold``:     Upper threshold in depth units (millimeter by default).
method
setKeypointRadius(self, arg0: int)
Set radius around keypoints to calculate spatial coordinates.  Parameter ``radius``:     Radius in pixels. $.. warning::  Only applicable to Keypoints or ImgDetections with keypoints.
method
setROIs(self, ROIs: list[SpatialLocationCalculatorConfigData])
Specify additional regions of interest (ROI) to calculate their spatial coordinates. Results of ROI coordinates are available on SpatialLocationCalculatorData output.  Parameter ``ROIs``:     Vector of configuration parameters for ROIs (region of interests)
method
setSegmentationPassthrough(self, arg0: bool)
Specify whether to passthrough segmentation mask along with spatial detections.  Parameter ``passthroughSegmentation``:     $.. warning::  Only applicable to ImgDetections with segmentation masks.
method
setStepSize(self, arg0: int)
Set step size for spatial location calculation. Step size 1 means that every pixel is taken into calculation, size 2 means every second etc. for AVERAGE, MIN, MAX step size is 1; for MODE/MEDIAN it's 2.
method
setUseSegmentation(self, arg0: bool)
Specify whether to consider only segmented pixels within a detection bounding box for spatial calculations.  Parameter ``useSegmentation``:     $.. warning::  Only applicable to ImgDetections with segmentation masks.
class

depthai.SpatialLocationCalculatorData(depthai.Buffer)

variable
method
method
method
getSpatialLocations(self) -> list[SpatialLocations]: list[SpatialLocations]
Retrieve configuration data for SpatialLocationCalculatorData.  Returns:     Vector of spatial location data, carrying spatial information (X,Y,Z)
class

depthai.SpatialLocations

method
property
config
Configuration for selected ROI
method
property
depthAverage
Average of depth values inside the ROI between the specified thresholds in config. Calculated only if calculation method is set to AVERAGE or MIN oR MAX.
method
property
depthAveragePixelCount
Number of depth values used in calculations.
method
property
depthMax
Maximum of depth values inside the ROI between the specified thresholds in config. Calculated only if calculation method is set to AVERAGE or MIN oR MAX.
method
property
depthMedian
Median of depth values inside the ROI between the specified thresholds in config. Calculated only if calculation method is set to MEDIAN.
method
property
depthMin
Minimum of depth values inside the ROI between the specified thresholds in config. Calculated only if calculation method is set to AVERAGE or MIN oR MAX.
method
property
depthMode
Most frequent of depth values inside the ROI between the specified thresholds in config. Calculated only if calculation method is set to MODE.
method
property
spatialCoordinates
Spatial coordinates - x,y,z; x,y are the relative positions of the center of ROI to the center of depth map
method
class

depthai.StereoDepthConfig(depthai.Buffer)

class
ConfidenceMetrics
Confidence metrics settings. RVC4 only.
class
class
PostProcessing
Post-processing filters, all the filters are applied in disparity domain.
class
CostAggregation
Cost Aggregation is based on Semi Global Block Matching (SGBM). This algorithm uses a semi global technique to aggregate the cost map. Ultimately the idea is to build inertia into the stereo algorithm. If a pixel has very little texture information, then odds are the correct disparity for this pixel is close to that of the previous pixel considered. This means that we get improved results in areas with low texture.
class
CostMatching
The matching cost is way of measuring the similarity of image locations in stereo correspondence algorithm. Based on the configuration parameters and based on the descriptor type, a linear equation is applied to computing the cost for each candidate disparity at each pixel.
class
CensusTransform
The basic cost function used by the Stereo Accelerator for matching the left and right images is the Census Transform. It works on a block of pixels and computes a bit vector which represents the structure of the image in that block. There are two types of Census Transform based on how the middle pixel is used: Classic Approach and Modified Census. The comparisons that are made between pixels can be or not thresholded. In some cases a mask can be applied to filter out only specific bits from the entire bit stream. All these approaches are: Classic Approach: Uses middle pixel to compare against all its neighbors over a defined window. Each comparison results in a new bit, that is 0 if central pixel is smaller, or 1 if is it bigger than its neighbor. Modified Census Transform: same as classic Census Transform, but instead of comparing central pixel with its neighbors, the window mean will be compared with each pixel over the window. Thresholding Census Transform: same as classic Census Transform, but it is not enough that a neighbor pixel to be bigger than the central pixel, it must be significant bigger (based on a threshold). Census Transform with Mask: same as classic Census Transform, but in this case not all of the pixel from the support window are part of the binary descriptor. We use a ma sk “M” to define which pixels are part of the binary descriptor (1), and which pixels should be skipped (0).
class
MedianFilter
Members:    MEDIAN_OFF    KERNEL_3x3    KERNEL_5x5    KERNEL_7x7
method
method
method
getBilateralFilterSigma(self) -> int: int
Get sigma value for 5x5 bilateral filter
method
getConfidenceThreshold(self) -> int: int
Get confidence threshold for disparity calculation
method
getCustomDepthUnitMultiplier(self) -> float: float
Get custom depth unit multiplier relative to 1 meter.
method
method
getExtendedDisparity(self) -> bool: bool
Get extended disparity setting
method
method
getLeftRightCheck(self) -> bool: bool
Get left-right check setting
method
getLeftRightCheckThreshold(self) -> int: int
Get threshold for left-right check combine
method
getMaxDisparity(self) -> float: float
Useful for normalization of the disparity map.  Returns:     Maximum disparity value that the node can return
method
method
method
getSubpixelFractionalBits(self) -> int: int
Get number of fractional bits for subpixel mode
method
setBilateralFilterSigma(self, sigma: int) -> StereoDepthConfig: StereoDepthConfig
A larger value of the parameter means that farther colors within the pixel neighborhood will be mixed together, resulting in larger areas of semi-equal color.  Parameter ``sigma``:     Set sigma value for 5x5 bilateral filter. 0..65535
method
setConfidenceThreshold(self, confThr: int) -> StereoDepthConfig: StereoDepthConfig
Confidence threshold for disparity calculation  Parameter ``confThr``:     Confidence threshold value 0..255
method
method
setDepthAlign(self, align: StereoDepthConfig.AlgorithmControl.DepthAlign) -> StereoDepthConfig: StereoDepthConfig
Parameter ``align``:     Set the disparity/depth alignment: centered (between the 'left' and 'right'     inputs), or from the perspective of a rectified output stream
method
setDepthUnit(self, arg0: LengthUnit) -> StereoDepthConfig: StereoDepthConfig
Set depth unit of depth map.  Meter, centimeter, millimeter, inch, foot or custom unit is available.
method
setDisparityShift(self, arg0: int) -> StereoDepthConfig: StereoDepthConfig
Shift input frame by a number of pixels to increase minimum depth. For example shifting by 48 will change effective disparity search range from (0,95] to [48,143]. An alternative approach to reducing the minZ. We normally only recommend doing this when it is known that there will be no objects farther away than MaxZ, such as having a depth camera mounted above a table pointing down at the table surface.
method
setExtendedDisparity(self, enable: bool) -> StereoDepthConfig: StereoDepthConfig
Disparity range increased from 95 to 190, combined from full resolution and downscaled images. Suitable for short range objects
method
method
setLeftRightCheck(self, enable: bool) -> StereoDepthConfig: StereoDepthConfig
Computes and combines disparities in both L-R and R-L directions, and combine them.  For better occlusion handling, discarding invalid disparity values
method
setLeftRightCheckThreshold(self, sigma: int) -> StereoDepthConfig: StereoDepthConfig
Parameter ``threshold``:     Set threshold for left-right, right-left disparity map combine, 0..255
method
setMedianFilter(self, median: filters.params.MedianFilter) -> StereoDepthConfig: StereoDepthConfig
Parameter ``median``:     Set kernel size for disparity/depth median filtering, or disable
method
setNumInvalidateEdgePixels(self, arg0: int) -> StereoDepthConfig: StereoDepthConfig
Invalidate X amount of pixels at the edge of disparity frame. For right and center alignment X pixels will be invalidated from the right edge, for left alignment from the left edge.
method
setSubpixel(self, enable: bool) -> StereoDepthConfig: StereoDepthConfig
Computes disparity with sub-pixel interpolation (3 fractional bits by default).  Suitable for long range. Currently incompatible with extended disparity
method
setSubpixelFractionalBits(self, subpixelFractionalBits: int) -> StereoDepthConfig: StereoDepthConfig
Number of fractional bits for subpixel mode. Default value: 3. Valid values: 3,4,5. Defines the number of fractional disparities: 2^x. Median filter postprocessing is supported only for 3 fractional bits.
property
algorithmControl
Controls the flow of stereo algorithm - left-right check, subpixel etc.
method
property
censusTransform
Census transform settings.
method
property
confidenceMetrics
Confidence metrics settings. RVC4 only.
method
property
costAggregation
Cost aggregation settings.
method
property
costMatching
Cost matching settings.
method
property
postProcessing
Controls the postprocessing of disparity and/or depth map.
method
class

depthai.StereoDepthConfig.ConfidenceMetrics

method
property
flatnessConfidenceThreshold
Threshold for flatness check in SGM block. Valid range is [1,7].
method
property
flatnessConfidenceWeight
Weight used with flatness estimation to generate final confidence map. Valid range is [0,32].
method
property
flatnessOverride
Flag to indicate whether final confidence value will be overidden by flatness value. Valid range is {true,false}.
method
property
motionVectorConfidenceThreshold
Threshold offset for MV variance in confidence generation. A value of 0 allows most variance. Valid range is [0,3].
method
property
motionVectorConfidenceWeight
Weight used with local neighborhood motion vector variance estimation to generate final confidence map. Valid range is [0,32].
method
property
occlusionConfidenceWeight
Weight used with occlusion estimation to generate final confidence map. Valid range is [0,32]
method
class

depthai.StereoDepthConfig.AlgorithmControl

class
DepthAlign
Align the disparity/depth to the perspective of a rectified output, or center it  Members:    AUTO    RECTIFIED_RIGHT :     RECTIFIED_LEFT :     CENTER :     RIGHT    LEFT
variable
method
property
customDepthUnitMultiplier
Custom depth unit multiplier, if custom depth unit is enabled, relative to 1 meter. A multiplier of 1000 effectively means depth unit in millimeter.
method
property
depthAlign
Set the disparity/depth alignment to the perspective of a rectified output, or center it
method
property
depthUnit
Measurement unit for depth data. Depth data is integer value, multiple of depth unit.
method
property
disparityShift
Shift input frame by a number of pixels to increase minimum depth. For example shifting by 48 will change effective disparity search range from (0,95] to [48,143]. An alternative approach to reducing the minZ. We normally only recommend doing this when it is known that there will be no objects farther away than MaxZ, such as having a depth camera mounted above a table pointing down at the table surface. RVC2 only.
method
property
enableExtended
Disparity range increased from 95 to 190, combined from full resolution and downscaled images. Suitable for short range objects
method
property
enableLeftRightCheck
Computes and combines disparities in both L-R and R-L directions, and combine them. For better occlusion handling
method
property
enableSubpixel
Computes disparity with sub-pixel interpolation (5 fractional bits), suitable for long range RVC2 only.
method
property
enableSwLeftRightCheck
Enables software left right check. RVC4 only.
method
property
leftRightCheckThreshold
Left-right check threshold for left-right, right-left disparity map combine, 0..128 Used only when left-right check mode is enabled. Defines the maximum difference between the confidence of pixels from left-right and right-left confidence maps
method
property
numInvalidateEdgePixels
Invalidate X amount of pixels at the edge of disparity frame. For right and center alignment X pixels will be invalidated from the right edge, for left alignment from the left edge. RVC2 only.
method
property
subpixelFractionalBits
Number of fractional bits for subpixel mode  Valid values: 3,4,5  Defines the number of fractional disparities: 2^x  Median filter postprocessing is supported only for 3 fractional bits RVC2 only.
method
class

depthai.StereoDepthConfig.PostProcessing

class
BrightnessFilter
Brightness filtering. If input frame pixel is too dark or too bright, disparity will be invalidated. The idea is that for too dark/too bright pixels we have low confidence, since that area was under/over exposed and details were lost.
class
DecimationFilter
Decimation filter. Reduces the depth scene complexity. The filter runs on kernel sizes [2x2] to [8x8] pixels.
class
HoleFilling
Hole-filling configuration. RVC4 only.
class
AdaptiveMedianFilter
Adaptive median filter configuration. RVC4 only.
class
Filter
Members:    NONE :     DECIMATION :     SPECKLE :     MEDIAN :     SPATIAL :     TEMPORAL : 
class
MedianFilter
Members:    MEDIAN_OFF    KERNEL_3x3    KERNEL_5x5    KERNEL_7x7
class
class
TemporalFilter
Temporal filtering with optional persistence.
class
ThresholdFilter
Threshold filtering. Filters out distances outside of a given interval.
class
method
property
adaptiveMedianFilter
Adaptive median filter configuration. RVC4 only.
method
property
bilateralSigmaValue
Sigma value for bilateral filter. 0 means disabled. A larger value of the parameter means that farther colors within the pixel neighborhood will be mixed together. RVC2 only.
method
property
brightnessFilter
Brightness filtering. If input frame pixel is too dark or too bright, disparity will be invalidated. The idea is that for too dark/too bright pixels we have low confidence, since that area was under/over exposed and details were lost.
method
property
decimationFilter
Decimation filter. Reduces disparity/depth map x/y complexity, reducing runtime complexity for other filters.
method
property
filteringOrder
Order of filters to be applied if filtering is enabled.
method
property
holeFilling
Hole-filling configuration. RVC4 only.
method
property
median
Set kernel size for disparity/depth median filtering, or disable
method
property
spatialFilter
Edge-preserving filtering: This type of filter will smooth the depth noise while attempting to preserve edges.
method
property
speckleFilter
Speckle filtering. Removes speckle noise.
method
property
temporalFilter
Temporal filtering with optional persistence.
method
property
thresholdFilter
Threshold filtering. Filters out distances outside of a given interval.
method
class

depthai.StereoDepthConfig.PostProcessing.BrightnessFilter

method
property
maxBrightness
Maximum range in depth units. If input pixel is less or equal than this value the depth value is invalidated.
method
property
minBrightness
Minimum pixel brightness. If input pixel is less or equal than this value the depth value is invalidated.
method
class

depthai.StereoDepthConfig.PostProcessing.HoleFilling

method
property
enable
Flag to enable post-processing hole-filling.
method
property
fillConfidenceThreshold
Pixels with confidence below this value will be filled with the average disparity of their corresponding superpixel. Valid range is [1,255].
method
property
highConfidenceThreshold
Pixels with confidence higher than this value are used to calculate an average disparity per superpixel. Valid range is [1,255]
method
property
invalidateDisparities
If enabled, sets to 0 the disparity of pixels with confidence below nFillConfThresh, which did not pass nMinValidPixels criteria. Valid range is {true, false}.
method
property
minValidDisparity
Represents the required percentange of pixels with confidence value above nHighConfThresh that are used to calculate average disparity per superpixel, where 1 means 50% or half, 2 means 25% or a quarter and 3 means 12.5% or an eighth. If the required number of pixels are not found, the holes will not be filled.
method
class

depthai.StereoDepthConfig.PostProcessing.AdaptiveMedianFilter

method
property
confidenceThreshold
Confidence threshold for adaptive median filtering. Should be less than nFillConfThresh value used in evaDfsHoleFillConfig. Valid range is [0,255].
method
property
enable
Flag to enable adaptive median filtering for a final pass of filtering on low confidence pixels.
method
class

depthai.StereoDepthConfig.PostProcessing.SpatialFilter

method
method
property
alpha
The Alpha factor in an exponential moving average with Alpha=1 - no filter. Alpha = 0 - infinite filter. Determines the amount of smoothing.
method
property
delta
Step-size boundary. Establishes the threshold used to preserve "edges". If the disparity value between neighboring pixels exceed the disparity threshold set by this delta parameter, then filtering will be temporarily disabled. Default value 0 means auto: 3 disparity integer levels. In case of subpixel mode it's 3*number of subpixel levels.
method
property
enable
Whether to enable or disable the filter.
method
property
holeFillingRadius
An in-place heuristic symmetric hole-filling mode applied horizontally during the filter passes. Intended to rectify minor artefacts with minimal performance impact. Search radius for hole filling.
method
property
numIterations
Number of iterations over the image in both horizontal and vertical direction.
method
class

depthai.StereoDepthConfig.PostProcessing.TemporalFilter

class
PersistencyMode
Persistency algorithm type.  Members:    PERSISTENCY_OFF :     VALID_8_OUT_OF_8 :     VALID_2_IN_LAST_3 :     VALID_2_IN_LAST_4 :     VALID_2_OUT_OF_8 :     VALID_1_IN_LAST_2 :     VALID_1_IN_LAST_5 :     VALID_1_IN_LAST_8 :     PERSISTENCY_INDEFINITELY : 
method
method
property
alpha
The Alpha factor in an exponential moving average with Alpha=1 - no filter. Alpha = 0 - infinite filter. Determines the extent of the temporal history that should be averaged.
method
property
delta
Step-size boundary. Establishes the threshold used to preserve surfaces (edges). If the disparity value between neighboring pixels exceed the disparity threshold set by this delta parameter, then filtering will be temporarily disabled. Default value 0 means auto: 3 disparity integer levels. In case of subpixel mode it's 3*number of subpixel levels.
method
property
enable
Whether to enable or disable the filter.
method
property
persistencyMode
Persistency mode. If the current disparity/depth value is invalid, it will be replaced by an older value, based on persistency mode.
method
class

depthai.StereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode

class

depthai.StereoDepthConfig.PostProcessing.ThresholdFilter

method
method
property
maxRange
Maximum range in depth units. Depth values over this value are invalidated.
method
property
minRange
Minimum range in depth units. Depth values under this value are invalidated.
method
class

depthai.StereoDepthConfig.PostProcessing.SpeckleFilter

method
method
property
differenceThreshold
Maximum difference between neighbor disparity pixels to put them into the same blob. Units in disparity integer levels.
method
property
enable
Whether to enable or disable the filter.
method
property
speckleRange
Speckle search range.
method
class

depthai.StereoDepthConfig.CostAggregation

class
P1Config
Adaptive P1 penalty configuration. RVC4 only.
class
P2Config
Adaptive P2 penalty configuration. RVC4 only.
method
property
divisionFactor
Cost calculation linear equation parameters. RVC2 only.
method
property
horizontalPenaltyCostP1
Horizontal P1 penalty cost parameter. RVC2 only.
method
property
horizontalPenaltyCostP2
Horizontal P2 penalty cost parameter. RVC2 only.
method
property
p1Config
Adaptive P1 penalty configuration. RVC4 only.
method
property
p2Config
Adaptive P2 penalty configuration. RVC4 only.
method
property
verticalPenaltyCostP1
Vertical P1 penalty cost parameter. RVC2 only.
method
property
verticalPenaltyCostP2
Vertical P2 penalty cost parameter. RVC2 only.
method
class

depthai.StereoDepthConfig.CostAggregation.P1Config

method
property
defaultValue
Used as the default penalty value when nAdapEnable is disabled. A bigger value enforces higher smoothness and reduced noise at the cost of lower edge accuracy. This value must be smaller than P2 default penalty. Valid range is [10,50].
method
property
edgeThreshold
Threshold value on edges when nAdapEnable is enabled. A bigger value permits higher neighboring feature dissimilarity tolerance. This value is shared with P2 penalty configuration. Valid range is [8,16].
method
property
edgeValue
Penalty value on edges when nAdapEnable is enabled. A smaller penalty value permits higher change in disparity. This value must be smaller than or equal to P2 edge penalty. Valid range is [10,50].
method
property
enableAdaptive
Used to disable/enable adaptive penalty.
method
property
smoothThreshold
Threshold value on low texture regions when nAdapEnable is enabled. A bigger value permits higher neighboring feature dissimilarity tolerance. This value is shared with P2 penalty configuration. Valid range is [2,12].
method
property
smoothValue
Penalty value on low texture regions when nAdapEnable is enabled. A smaller penalty value permits higher change in disparity. This value must be smaller than or equal to P2 smoothness penalty. Valid range is [10,50].
method
class

depthai.StereoDepthConfig.CostAggregation.P2Config

method
property
defaultValue
Used as the default penalty value when nAdapEnable is disabled. A bigger value enforces higher smoothness and reduced noise at the cost of lower edge accuracy. This value must be larger than P1 default penalty. Valid range is [20,100].
method
property
edgeValue
Penalty value on edges when nAdapEnable is enabled. A smaller penalty value permits higher change in disparity. This value must be larger than or equal to P1 edge penalty. Valid range is [20,100].
method
property
enableAdaptive
Used to disable/enable adaptive penalty.
method
property
smoothValue
Penalty value on low texture regions when nAdapEnable is enabled. A smaller penalty value permits higher change in disparity. This value must be larger than or equal to P1 smoothness penalty. Valid range is [20,100].
method
class

depthai.StereoDepthConfig.CostMatching

class
LinearEquationParameters
The linear equation applied for computing the cost is: COMB_COST = α*AD + β*(CTC<<3). CLAMP(COMB_COST >> 5, threshold). Where AD is the Absolute Difference between 2 pixels values. CTC is the Census Transform Cost between 2 pixels, based on Hamming distance (xor). The α and β parameters are subject to fine tuning by the user. RVC2 only.
class
DisparityWidth
Disparity search range: 64 or 96 pixels are supported by the HW.  Members:    DISPARITY_64 :     DISPARITY_96 : 
method
property
confidenceThreshold
Disparities with confidence value over this threshold are accepted.
method
property
disparityWidth
Disparity search range, default 96 pixels. RVC2 only.
method
property
enableCompanding
Disparity companding using sparse matching. Matching pixel by pixel for N disparities. Matching every 2nd pixel for M disparitites. Matching every 4th pixel for T disparities. In case of 96 disparities: N=48, M=32, T=16. This way the search range is extended to 176 disparities, by sparse matching. Note: when enabling this flag only depth map will be affected, disparity map is not. RVC2 only.
method
property
enableSwConfidenceThresholding
Enable software confidence thresholding. RVC4 only.
method
property
invalidDisparityValue
Used only for debug purposes, SW postprocessing handled only invalid value of 0 properly. RVC2 only.
method
property
linearEquationParameters
Cost calculation linear equation parameters. RVC2 only.
method
class

depthai.StereoDepthConfig.CostMatching.LinearEquationParameters

class

depthai.StereoDepthConfig.CensusTransform

class
KernelSize
Census transform kernel size possible values.  Members:    AUTO :     KERNEL_5x5 :     KERNEL_7x7 :     KERNEL_7x9 : 
method
property
enableMeanMode
If enabled, each pixel in the window is compared with the mean window value instead of the central pixel. RVC2 only.
method
property
kernelMask
Census transform mask, default - auto, mask is set based on resolution and kernel size. Disabled for 400p input resolution. Enabled for 720p. 0XA82415 for 5x5 census transform kernel. 0XAA02A8154055 for 7x7 census transform kernel. 0X2AA00AA805540155 for 7x9 census transform kernel. Empirical values. RVC2 only.
method
property
kernelSize
Census transform kernel size. RVC2 only.
method
property
noiseThresholdOffset
Used to reduce small fixed levels of noise across all luminance values in the current image. Valid range is [0,127]. Default value is 1. RVC4 only.
method
property
noiseThresholdScale
Used to reduce noise values that increase with luminance in the current image. Valid range is [-128,127]. Default value is 1. RVC4 only.
method
property
threshold
Census transform comparison threshold value. RVC2 only.
method
class

depthai.TrackedFeature

method
property
age
Feature age in frames
method
property
descriptor
Feature descriptor
method
property
harrisScore
Feature harris score
method
property
id
Feature ID. Persistent between frames if motion estimation is enabled.
method
property
position
x, y position of the detected feature
method
property
trackingError
Feature tracking error
method
class

depthai.TrackedFeatures(depthai.Buffer)

class

depthai.Tracklets(depthai.Buffer, depthai.Transformable)

method
method
method
method
method
transformTo(self, target: ImgTransformation) -> Tracklets: Tracklets
Returns a new Tracklets message with the tracklets transformed into the target image transformation.  For each tracklet, the bounding box is assumed to lie on a plane parallel to the image plane at depth `tracklet.spatialCoordinates.z` (that is, all four bounding-box corners are projected using the same depth value). The transformed corners are then fit with the smallest enclosing rotated rectangle to preserve rectangularity.  Parameter ``target``:     Target image transformation.
property
tracklets
Retrieve data for Tracklets.  Returns:     Vector of object tracker data, carrying tracking information.
method
property
unit
Measurement unit used by all tracklets' `spatialCoordinates` in this list.
method
class

depthai.BenchmarkReport(depthai.Buffer)

class

depthai.PointCloudConfig(depthai.Buffer)

class
CoordinateSystemType
Members:    DEFAULT    CAMERA_SOCKET    HOUSING
method
method
method
method
getLengthUnit(self) -> LengthUnit: LengthUnit
Retrieve the length unit used for output point coordinates.
method
getOrganized(self) -> bool: bool
Retrieve whether the point cloud is organized (all width*height points kept).  Returns:     true if all width*height points are output, false if only valid (z > 0)     points are kept
method
getSparse(self) -> bool: bool
**Deprecated:** Use getOrganized() instead (sparse == !organized).
method
getTargetCameraSocket(self) -> CameraBoardSocket: CameraBoardSocket
Retrieve the target camera socket (valid when coordSystemType == CAMERA_SOCKET).
method
getTargetHousingCS(self) -> HousingCoordinateSystem: HousingCoordinateSystem
Retrieve the target housing coordinate system (valid when coordSystemType == HOUSING).
method
method
getUseSpecTranslation(self) -> bool: bool
Retrieve whether spec translation is used.
method
method
setOrganized(self, arg0: bool) -> PointCloudConfig: PointCloudConfig
Enable or disable organized point cloud output. When true all width*height points are kept; when false only points with z > 0 are emitted.
method
setSparse(self, sparse: bool) -> PointCloudConfig: PointCloudConfig
**Deprecated:** Use setOrganized() instead (sparse == !organized).
method
method
class

depthai.PointCloudData(depthai.Buffer, depthai.ProtoSerializable, depthai.Transformable)

method
method
method
getHeight(self) -> int: int
Retrieves the height in pixels - in case of a sparse point cloud, this represents the hight of the frame which was used to generate the point cloud
method
getInstanceNum(self) -> int: int
Retrieves instance number
method
getMaxX(self) -> float: float
Retrieves maximal x coordinate in depth units (millimeter by default)
method
getMaxY(self) -> float: float
Retrieves maximal y coordinate in depth units (millimeter by default)
method
getMaxZ(self) -> float: float
Retrieves maximal z coordinate in depth units (millimeter by default)
method
getMinX(self) -> float: float
Retrieves minimal x coordinate in depth units (millimeter by default)
method
getMinY(self) -> float: float
Retrieves minimal y coordinate in depth units (millimeter by default)
method
getMinZ(self) -> float: float
Retrieves minimal z coordinate in depth units (millimeter by default)
method
method
method
method
getWidth(self) -> int: int
Retrieves the height in pixels - in case of a sparse point cloud, this represents the hight of the frame which was used to generate the point cloud
method
isColor(self) -> bool: bool
Retrieves whether point cloud is color
method
isOrganized(self) -> bool: bool
Retrieves whether point cloud is organized (height > 1) Organized point clouds have width x height structure from the original image Sparse point clouds have height == 1 and only contain valid points
method
isSparse(self) -> bool: bool
Retrieves whether point cloud is sparse $.. deprecated::  Use isOrganized() instead. Sparse means height == 1
method
setHeight(self, arg0: int) -> PointCloudData: PointCloudData
Specifies frame height  Parameter ``height``:     frame height
method
setInstanceNum(self, instanceNum: int) -> PointCloudData: PointCloudData
Specifies instance number  Parameter ``instanceNum``:     instance number
method
setMaxX(self, arg0: float) -> PointCloudData: PointCloudData
Specifies maximal x coordinate in depth units (millimeter by default)  Parameter ``val``:     maximal x coordinate in depth units (millimeter by default)
method
setMaxY(self, arg0: float) -> PointCloudData: PointCloudData
Specifies maximal y coordinate in depth units (millimeter by default)  Parameter ``val``:     maximal y coordinate in depth units (millimeter by default)
method
setMaxZ(self, arg0: float) -> PointCloudData: PointCloudData
Specifies maximal z coordinate in depth units (millimeter by default)  Parameter ``val``:     maximal z coordinate in depth units (millimeter by default)
method
setMinX(self, arg0: float) -> PointCloudData: PointCloudData
Specifies minimal x coordinate in depth units (millimeter by default)  Parameter ``val``:     minimal x coordinate in depth units (millimeter by default)
method
setMinY(self, arg0: float) -> PointCloudData: PointCloudData
Specifies minimal y coordinate in depth units (millimeter by default)  Parameter ``val``:     minimal y coordinate in depth units (millimeter by default)
method
setMinZ(self, arg0: float) -> PointCloudData: PointCloudData
Specifies minimal z coordinate in depth units (millimeter by default)  Parameter ``val``:     minimal z coordinate in depth units (millimeter by default)
method
method
method
method
method
setWidth(self, arg0: int) -> PointCloudData: PointCloudData
Specifies frame width  Parameter ``width``:     frame width
method
updateBoundingBox(self) -> PointCloudData: PointCloudData
Recomputes the bounding box (min/max X, Y, Z) from the current point data. All stored points are included regardless of their z value. If the cloud is empty, all bounds are set to 0.
class

depthai.PipelineEvent(depthai.Buffer)

class
Type
Members:    CUSTOM    LOOP    INPUT    OUTPUT    INPUT_BLOCK    OUTPUT_BLOCK
class
Interval
Members:    NONE    START    END
class
Status
Members:    SUCCESS    BLOCKED    CANCELLED
variable
variable
variable
variable
variable
variable
method
method
class

depthai.NodeState.DurationEvent

class

depthai.PipelineState(depthai.Buffer)

class

depthai.ImageAlignConfig(depthai.Buffer)

method
method
property
staticDepthPlane
Optional static depth plane to align to, in depth units, by default millimeters
method
class

depthai.AlignConfig(depthai.Buffer)

method
method
property
staticDepthPlane
Optional static depth plane to align to, in depth units, by default millimeters
method
class

depthai.CircleAnnotation

class

depthai.TextAnnotation

class

depthai.MapData(depthai.Buffer)

class

depthai.CalibrationMetrics(depthai.Buffer)

class

depthai.DynamicCalibrationControl(depthai.Buffer)

class
class
PerformanceMode
Members:    DEFAULT    STATIC_SCENERY    OPTIMIZE_SPEED    OPTIMIZE_PERFORMANCE    SKIP_CHECKS    RELAXED_COVERAGE
variable
variable
variable
variable
variable
variable
static method
static method
static method
static method
static method
static method
static method
static method
static method
DynamicCalibrationControl.stopCalibration() -> DynamicCalibrationControl: DynamicCalibrationControl
Create a DynamicCalibrationControl with a StopCalibration command.
method
class

depthai.DynamicCalibrationControl.Commands

class

depthai.DynamicCalibrationControl.Commands.Calibrate

class

depthai.DynamicCalibrationControl.Commands.ComputeCalibrationMetrics

class

depthai.DynamicCalibrationControl.Commands.CalibrationQuality

class

depthai.DynamicCalibrationControl.Commands.StopCalibration

class

depthai.DynamicCalibrationControl.Commands.LoadImage

class

depthai.DynamicCalibrationControl.Commands.ApplyCalibration

class

depthai.DynamicCalibrationControl.Commands.ResetData

class

depthai.AutoCalibrationConfig(depthai.Buffer)

class
Mode
Defines when the auto-calibration process should be triggered.  Members:    ON_START    CONTINUOUS
variable
variable
method
method
property
calibrationConfidenceThreshold
Minimum confidence score (0.0 to 1.0) required to apply a new calibration.
method
property
dataConfidenceThreshold
Minimum quality threshold (0.0 to 1.0) for input features to be used. A value below 0 selects the default based on the lens model.
method
property
flashCalibration
If true, saves successful calibration to non-volatile memory (EEPROM); otherwise, keeps in RAM only.
method
property
maxImagesPerRecalibration
Maximum number of images to collect for one recalibration event.
method
property
maxIterations
Maximum number of optimization iterations per calibration cycle.
method
property
mode
Calibration trigger mode (ON_START or CONTINUOUS).
method
property
sleepingTime
Seconds to sleep between calibration cycles in CONTINUOUS mode.
method
property
validationSetSize
Number of images used for validating the calibration result.
method
class

depthai.LogMessage

class

depthai.MessageQueue

exception
static method
static method
method
method
addCallback(self, callback: typing.Callable) -> int: int
Adds a callback on message received  Parameter ``callback``:     Callback function with queue name and message pointer  Returns:     Callback id
method
close(self)
Closes the queue and unblocks any waiting consumers or producers
method
front(self) -> ADatatype: ADatatype
Gets first message in the queue.  Returns:     Message of type T or nullptr if no message available
method
method
getAll(self) -> list[ADatatype]: list[ADatatype]
Block until at least one message in the queue. Then return all messages from the queue.  Returns:     Vector of messages which can either be of type T or nullptr
method
getBlocking(self) -> bool: bool
Gets current queue behavior when full (maxSize)  Returns:     True if blocking, false otherwise
method
getMaxSize(self) -> int: int
Gets queue maximum size  Returns:     Maximum queue size
method
method
getSize(self) -> int: int
Gets queue current size  Returns:     Current queue size
method
has(self) -> bool: bool
Check whether front of the queue has message of type T  Returns:     True if queue isn't empty and the first element is of type T, false     otherwise
method
isClosed(self) -> bool: bool
Check whether queue is closed
method
isFull(self) -> int: int
Gets whether queue is full  Returns:     True if queue is full, false otherwise
method
removeCallback(self, callbackId: int) -> bool: bool
Removes a callback  Parameter ``callbackId``:     Id of callback to be removed  Returns:     True if callback was removed, false otherwise
method
method
setBlocking(self, blocking: bool)
Sets queue behavior when full (maxSize)  Parameter ``blocking``:     Specifies if block or overwrite the oldest message in the queue
method
setMaxSize(self, maxSize: int)
Sets queue maximum size  Parameter ``maxSize``:     Specifies maximum number of messages in the queue @note If maxSize is     smaller than size, queue will not be truncated immediately, only after     messages are popped
method
setName(self, name: str)
Set the name of the queue
method
tryGet(self) -> ADatatype: ADatatype
Try to retrieve message T from queue. If message isn't of type T it returns nullptr  Returns:     Message of type T or nullptr if no message available
method
tryGetAll(self) -> list[ADatatype]: list[ADatatype]
Try to retrieve all messages in the queue.  Returns:     Vector of messages which can either be of type T or nullptr
method
trySend(self, msg: ADatatype) -> bool: bool
Tries sending a message  Parameter ``msg``:     message to send
class

depthai.OpenVINO

class
Version
OpenVINO Version supported version information  Members:    VERSION_2020_3    VERSION_2020_4    VERSION_2021_1    VERSION_2021_2    VERSION_2021_3    VERSION_2021_4    VERSION_2022_1    VERSION_UNIVERSAL
class
Blob
OpenVINO Blob
class
SuperBlob
A superblob is an efficient way of storing generated blobs for all different number of shaves.
class
Device
Members:    VPU    VPUX
variable
variable
variable
variable
variable
variable
variable
variable
variable
static method
static method
OpenVINO.getBlobLatestSupportedVersion()
Returns latest potentially supported version by a given blob version.  Parameter ``majorVersion``:     Major version from OpenVINO blob  Parameter ``minorVersion``:     Minor version from OpenVINO blob  Returns:     Latest potentially supported version
static method
OpenVINO.getBlobSupportedVersions()
Returns a list of potentially supported versions for a specified blob major and minor versions.  Parameter ``majorVersion``:     Major version from OpenVINO blob  Parameter ``minorVersion``:     Minor version from OpenVINO blob  Returns:     Vector of potentially supported versions
static method
OpenVINO.getVersionName(version: OpenVINO.Version) -> str: str
Returns string representation of a given version  Parameter ``version``:     OpenVINO version  Returns:     Name of a given version
static method
static method
OpenVINO.parseVersionName(versionString: str) -> OpenVINO.Version: OpenVINO.Version
Creates Version from string representation. Throws if not possible.  Parameter ``versionString``:     Version as string  Returns:     Version object if successful
class

depthai.OpenVINO.Blob

method
property
data
Blob data
method
property
device
Device for which the blob is compiled for
method
property
networkInputs
Map of input names to additional information
method
property
networkOutputs
Map of output names to additional information
method
property
numShaves
Number of shaves the blob was compiled for
method
property
numSlices
Number of CMX slices the blob was compiled for
method
property
stageCount
Number of network stages
method
property
version
OpenVINO version
method
class

depthai.OpenVINO.SuperBlob

constant
method
method
getBlobWithNumShaves(self, numShaves: int) -> OpenVINO.Blob: OpenVINO.Blob
Generate a blob with a specific number of shaves  Parameter ``numShaves:``:     Number of shaves to generate the blob for. Must be between 1 and     NUMBER_OF_PATCHES.  Returns:     dai::OpenVINO::Blob: Blob compiled for the specified number of shaves
class

depthai.NNArchive

method
method
getBlob(self) -> OpenVINO.Blob|None: OpenVINO.Blob|None
Return a SuperVINO::Blob from the archive if getModelType() returns BLOB, nothing otherwise  Returns:     std::optional<OpenVINO::Blob>: Model blob
method
getConfig(self) -> nn_archive.v1.Config: nn_archive.v1.Config
Get NNArchive config.  Template parameter ``T:``:     Type of config to get  Returns:     const T&: Config
method
getConfigV1(self) -> nn_archive.v1.Config: nn_archive.v1.Config
Get NNArchive config.  Template parameter ``T:``:     Type of config to get  Returns:     const T&: Config
method
getHeadConfig(self, index: int = 0) -> nn_archive.v1.Head: nn_archive.v1.Head
Get specific head configuration from NNArchive.  Parameter ``headIndex:``:     Index of the head to retrieve  Returns:     dai::nn_archive::v1::Head: Head configuration
method
getInputHeight(self, index: int = 0) -> int|None: int|None
Get inputHeight of the model  Parameter ``index:``:     Index of input  Returns:     int: inputHeight
method
getInputSize(self, index: int = 0) -> tuple[int, int]|None: tuple[int, int]|None
Get inputSize of the model  Parameter ``index:``:     Index of input @note this function is only valid for models with NCHW and     NHWC input formats  Returns:     std::vector<std::pair<int, int>>: inputSize
method
getInputWidth(self, index: int = 0) -> int|None: int|None
Get inputWidth of the model  Parameter ``index:``:     Index of input  Returns:     int: inputWidth
method
getModelType(self) -> ModelType: ModelType
Get type of model contained in NNArchive  Returns:     model::ModelType: type of model in archive
method
getOtherModelFormat(self) -> typing.Any: typing.Any
Return a model from the archive if getModelType() returns OTHER or DLC, nothing otherwise  Returns:     std::optional<std::vector<uint8_t>>: Model
method
getSuperBlob(self) -> OpenVINO.SuperBlob|None: OpenVINO.SuperBlob|None
Return a SuperVINO::Blob from the archive if getModelType() returns BLOB, nothing otherwise  Returns:     std::optional<OpenVINO::Blob>: Model blob
method
getSupportedPlatforms(self) -> list[Platform]: list[Platform]
Get supported platforms  Returns:     std::vector<dai::Platform>: Supported platforms
class

depthai.NNArchiveOptions

class

depthai.NNArchiveEntry

class
Compression
Members:    AUTO    RAW_FS    TAR    TAR_GZ    TAR_XZ
class
Seek
Members:    SET    CUR    END
class

depthai.Node

class
class
class
class
Id
Node identificator. Unique for every node on a single Pipeline
class
Connection
Connection between an Input and Output
class
class
method
add(self, node: Node)
Add existing node to nodeMap
method
method
method
method
method
getName(self) -> str: str
Retrieves nodes name
method
method
method
method
method
property
id
Id of node. Assigned after being placed on the pipeline
class

depthai.Node.Input(depthai.MessageQueue)

class
Type
Members:    SReceiver    MReceiver
variable
method
method
createInputQueue(self, maxSize: int = 16, blocking: bool = False) -> InputQueue: InputQueue
Create an shared pointer to an input queue that can be used to send messages to this input from onhost  Parameter ``maxSize:``:     Maximum size of the input queue  Parameter ``blocking:``:     Whether the input queue should block when full  Returns:     std::shared_ptr<InputQueue>: shared pointer to an input queue
method
method
method
getReusePreviousMessage(self) -> bool: bool
Equivalent to getWaitForMessage but with inverted logic.
method
getSourceDevice(self) -> Device: Device
Get the device that produces the data arriving at this input, resolved at pipeline build.  Returns:     The source device, or nullptr when the upstream node runs on the host.     Throws if this input is connected to sources on more than one device.
method
getWaitForMessage(self) -> bool: bool
Get behavior whether to wait for this input when a Node processes certain data or not  Returns:     Whether to wait for message to arrive to this input or not
method
getXLinkBridge(self) -> node.internal.XLinkInBridge: node.internal.XLinkInBridge
Get XLink bridge associated with this input (only valid for device inputs after pipeline build)  Returns:     std::shared_ptr<dai::node::internal::XLinkInBridge>: pointer to the XLink     bridge or nullptr if not applicable
method
method
setReusePreviousMessage(self, reusePreviousMessage: bool)
Equivalent to setWaitForMessage but with inverted logic.
method
setWaitForMessage(self, waitForMessage: bool)
Overrides default wait for message behavior. Applicable for nodes with multiple inputs. Specifies behavior whether to wait for this input when a Node processes certain data or not.  Parameter ``waitForMessage``:     Whether to wait for message to arrive to this input or not
class

depthai.Node.Output

class
Type
Members:    MSender    SSender
method
method
canConnect(self, input: Node.Input) -> bool: bool
Check if connection is possible  Parameter ``in``:     Input to connect to  Returns:     True if connection is possible, false otherwise
method
createOutputQueue(self, maxSize: int = 16, blocking: bool = False) -> MessageQueue: MessageQueue
Construct and return a shared pointer to an output message queue  Parameter ``maxSize:``:     Maximum size of the output queue  Parameter ``blocking:``:     Whether the output queue should block when full  Returns:     std::shared_ptr<dai::MessageQueue>: shared pointer to an output queue
method
getName(self) -> str: str
Get name of the output
method
method
method
getXLinkBridge(self) -> node.internal.XLinkOutBridge: node.internal.XLinkOutBridge
Get XLink bridge associated with this output (only valid for device outputs after pipeline build)  Returns:     std::shared_ptr<dai::node::internal::XLinkOutBridge>: pointer to the XLink     bridge or nullptr if not applicable
method
isSamePipeline(self, input: Node.Input) -> bool: bool
Check if this output and given input are on the same pipeline.  See also:     canConnect for checking if connection is possible  Returns:     True if output and input are on the same pipeline
method
method
send(self, msg: ADatatype)
Sends a Message to all connected inputs  Parameter ``msg``:     Message to send to all connected inputs
method
method
trySend(self, msg: ADatatype) -> bool: bool
Try sending a message to all connected inputs  Parameter ``msg``:     Message to send to all connected inputs  Returns:     True if ALL connected inputs got the message, false otherwise
method
class

depthai.Node.DatatypeHierarchy

class

depthai.Node.Connection

class

depthai.InputQueue

method
send(self, msg: ADatatype)
Send a message to the connected input  Parameter ``msg:``:     Message to send
method
trySend(self, msg: ADatatype) -> bool: bool
Try to send a message to the connected input, without waiting for space in the queue  Parameter ``msg:``:     Message to send  Returns:     True if the message was queued, false if the queue was full
class

depthai.ThreadedNode(depthai.Node)

method
blockEvent(self, type: PipelineEvent.Type, source: str) -> BlockPipelineEvent: BlockPipelineEvent
Creates a scoped event that sends start and end events for a custom block event  Parameter ``type``:     Type of the event  Parameter ``source``:     Source name of the event
method
method
method
method
getLogLevel(self) -> LogLevel: LogLevel
Gets the logging severity level for this node.  Returns:     Logging severity level
method
method
inputBlockEvent(self) -> BlockPipelineEvent: BlockPipelineEvent
Creates a scoped event that sends start and end events for the getting inputs state
method
method
method
outputBlockEvent(self) -> BlockPipelineEvent: BlockPipelineEvent
Creates a scoped event that sends start and end events for the sending outputs state
method
setLogLevel(self, arg0: LogLevel)
Sets the logging severity level for this node.  Parameter ``level``:     Logging severity level
method
method
property
class

depthai.DeviceNode(depthai.ThreadedNode)

method
getDevice(self) -> Device: Device
Get device for this node  Returns:     shared pointer to device
class

depthai.ColorCameraProperties

class
SensorResolution
Select the camera sensor resolution  Members:    THE_1080_P    THE_1200_P    THE_4_K    THE_5_MP    THE_12_MP    THE_4000X3000    THE_13_MP    THE_5312X6000    THE_48_MP    THE_720_P    THE_800_P    THE_240X180    THE_1280X962    THE_2000X1500    THE_2028X1520    THE_2104X1560    THE_1440X1080    THE_1352X1012    THE_2024X1520
class
ColorOrder
For 24 bit color these can be either RGB or BGR  Members:    BGR    RGB
class
WarpMeshSource
Warp mesh source  Members:    AUTO    NONE    CALIBRATION    URI
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
class

depthai.ColorCameraProperties.SensorResolution

variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
method
method
method
method
method
method
method
method
method
method
property
property
class

depthai.MonoCameraProperties

class
SensorResolution
Select the camera sensor resolution: 1280×720, 1280×800, 640×400, 640×480, 1920×1200, ...  Members:    THE_720_P    THE_800_P    THE_400_P    THE_480_P    THE_1200_P    THE_4000X3000    THE_4224X3136
variable
variable
variable
variable
variable
variable
variable
variable
class

depthai.StereoDepthProperties

class
property
alphaScaling
Free scaling parameter between 0 (when all the pixels in the undistorted image are valid) and 1 (when all the source image pixels are retained in the undistorted image). On some high distortion lenses, and/or due to rectification (image rotated) invalid areas may appear even with alpha=0, in these cases alpha < 0.0 helps removing invalid areas.  .. warning::     On RVC4 the DEFAULT, DENSITY, and FAST_DENSITY presets can produce     inaccurate depth in black padded regions, as they prioritize coverage.  See getOptimalNewCameraMatrix from opencv for more details.
method
property
baseline
Override baseline from calibration. Used only in disparity to depth conversion. Units are centimeters.
method
property
depthAlignCamera
Which camera to align disparity/depth to. When configured (not AUTO), takes precedence over 'depthAlign'
method
property
depthAlignmentUseSpecTranslation
Use baseline information for depth alignment from specs (design data) or from calibration. Suitable for debugging. Utilizes calibrated value as default
method
property
disparityToDepthUseSpecTranslation
Use baseline information for disparity to depth conversion from specs (design data) or from calibration. Suitable for debugging. Utilizes calibrated value as default
method
property
enableRectification
Enable stereo rectification/dewarp or not. Useful to disable when replaying pre- recorded rectified frames.
method
property
enableRuntimeStereoModeSwitch
Whether to enable switching stereo modes at runtime or not. E.g. standard to subpixel, standard+LR-check to subpixel + LR-check. Note: It will allocate resources for worst cases scenario, should be enabled only if dynamic mode switch is required. Default value: false. RVC2 only.
method
property
focalLength
Override focal length from calibration. Used only in disparity to depth conversion. Units are pixels.
method
property
focalLengthFromCalibration
Whether to use horizontal focal length from calibration intrinsics (fx) or calculate based on calibration FOV. Default value is true. If set to false it's calculated from FOV and image resolution: focalLength = calib.width / (2.f * tan(calib.fov / 2 / 180.f * pi));
method
property
height
Input frame height. Optional (taken from MonoCamera nodes if they exist)
method
property
initialConfig
Initial stereo config
method
property
mesh
Specify a direct warp mesh to be used for rectification, instead of intrinsics + extrinsic matrices
method
property
numFramesPool
Num frames in output pool
method
property
numPostProcessingMemorySlices
Number of memory slices reserved for stereo depth post processing. -1 means auto, memory will be allocated based on initial stereo settings and number of shaves. 0 means that it will reuse the memory slices assigned for main stereo algorithm. For optimal performance it's recommended to allocate more than 0, so post processing will run in parallel with main stereo algorithm. Minimum 1, maximum 6. RVC2 only.
method
property
numPostProcessingShaves
Number of shaves reserved for stereo depth post processing. Post processing can use multiple shaves to increase performance. -1 means auto, resources will be allocated based on enabled filters. 0 means that it will reuse the shave assigned for main stereo algorithm. For optimal performance it's recommended to allocate more than 0, so post processing will run in parallel with main stereo algorithm. Minimum 1, maximum 10. RVC2 only.
method
property
outHeight
Output disparity/depth height. Currently only used when aligning to RGB
method
property
outKeepAspectRatio
Whether to keep aspect ratio of the input (rectified) or not
method
property
outWidth
Output disparity/depth width. Currently only used when aligning to RGB
method
property
rectificationUseSpecTranslation
Obtain rectification matrices using spec translation (design data) or from calibration in calculations. Suitable for debugging. Default: false
method
property
rectifyEdgeFillColor
Fill color for missing data at frame edges - grayscale 0..255, or -1 to replicate pixels
method
property
useHomographyRectification
Use 3x3 homography matrix for stereo rectification instead of sparse mesh generated on device. Default behaviour is AUTO, for lenses with FOV over 85 degrees sparse mesh is used, otherwise 3x3 homography. If custom mesh data is provided through loadMeshData or loadMeshFiles this option is ignored. true: 3x3 homography matrix generated from calibration data is used for stereo rectification, can't correct lens distortion. false: sparse mesh is generated on-device from calibration data with mesh step specified with setMeshStep (Default: (16, 16)), can correct lens distortion. Implementation for generating the mesh is same as opencv's initUndistortRectifyMap function. Only the first 8 distortion coefficients are used from calibration data.
method
property
width
Input frame width. Optional (taken from MonoCamera nodes if they exist)
method
class

depthai.StereoDepthProperties.RectificationMesh

property
meshLeftUri
Uri which points to the mesh array for 'left' input rectification
method
property
meshRightUri
Uri which points to the mesh array for 'right' input rectification
method
property
meshSize
Mesh array size in bytes, for each of 'left' and 'right' (need to match)
method
property
stepHeight
Distance between mesh points, in the vertical direction
method
property
stepWidth
Distance between mesh points, in the horizontal direction
method
class

depthai.NeuralNetworkProperties

class

depthai.VideoEncoderProperties

class
Profile
Encoding profile, H264 (AVC), H265 (HEVC) or MJPEG  Members:    H264_BASELINE    H264_HIGH    H264_MAIN    H265_MAIN    MJPEG
class
RateControlMode
Rate control mode specifies if constant or variable bitrate should be used (H264 / H265)  Members:    CBR    VBR
variable
variable
variable
variable
variable
variable
variable
variable
variable
class

depthai.ImageManipProperties

class

depthai.SPIOutProperties

class

depthai.SPIInProperties

class

depthai.SystemLoggerProperties

class

depthai.ScriptProperties

property
processor
Which processor should execute the script
method
property
scriptName
Name of script
method
property
scriptUri
Uri which points to actual script
method
class

depthai.SpatialLocationCalculatorProperties

class

depthai.ObjectTrackerProperties

property
detectionLabelsToTrack
Which detections labels to track. Default all labels are tracked.
method
property
maxObjectsToTrack
Maximum number of objects to track. Maximum 60 for SHORT_TERM_KCF, maximum 1000 for other tracking methods. Default 60.
method
property
spatialAssociation
Whether to use spatial coordinates in association when available.
method
property
spatialAssociationWeight
Weight for spatial distance in association cost [0,1].
method
property
spatialDepthAwareScale
Depth-aware gating scale. Gate grows with depth: gate = base * (1 + scale * depthMeters).
method
property
spatialDistanceThreshold
Base 3D gating threshold in meters used for spatial association.
method
property
trackerIdAssignmentPolicy
New ID assignment policy.
method
property
trackerThreshold
Confidence threshold for tracklets. Above this threshold detections will be tracked. Default 0, all detections are tracked.
method
property
trackerType
Tracking method.
method
class

depthai.IMUProperties

variable
variable
variable
property
enableFirmwareUpdate
Whether to perform firmware update or not. Default value: false.
method
class

depthai.EdgeDetectorProperties

property
initialConfig
Initial edge detector config
method
property
numFramesPool
Num frames in output pool
method
property
outputFrameSize
Maximum output frame size in bytes (eg: 300x300 BGR image -> 300*300*3 bytes)
method
class

depthai.FeatureTrackerProperties

property
initialConfig
Initial feature tracker config
method
property
numMemorySlices
Number of memory slices reserved for feature tracking. Optical flow can use 1 or 2 memory slices, while for corner detection only 1 is enough. Maximum number of features depends on the number of allocated memory slices. Hardware motion estimation doesn't require memory slices. Maximum 2, minimum 1.
method
property
numShaves
Number of shaves reserved for feature tracking. Optical flow can use 1 or 2 shaves, while for corner detection only 1 is enough. Hardware motion estimation doesn't require shaves. Maximum 2, minimum 1.
method
class

depthai.AprilTagProperties

variable
property
inputConfigSync
Whether to wait for config at 'inputConfig' IO
method
property
numThreads
How many threads to use for AprilTag detection
method
class

depthai.DetectionParserProperties

class

depthai.SegmentationParserProperties

class

depthai.ThermalProperties

property
boardSocket
Which socket will color camera use
method
property
fps
Camera sensor FPS
method
property
initialConfig
Initial Thermal config
method
property
numFramesPool
Num frames in output pool
method
class

depthai.ToFProperties

property
enableUndistortion
Undistort depth and auxiliary outputs before publishing them.
method
property
initialConfig
Initial ToF config
method
property
numFramesPool
Num frames in output pool
method
property
numShaves
Number of shaves reserved for ToF decoding.
method
property
warpHwIds
Warp HW IDs to use for undistortion, if empty, use auto/default
method
class

depthai.PointCloudProperties

class

depthai.MessageDemuxProperties

property
processor
Which processor should execute the node.
method
class

depthai.ImageFiltersConfig(depthai.Buffer)

method
method
insertFilter(self, params: ...|...|...|...) -> ImageFiltersConfig: ImageFiltersConfig
Insert filter parameters describing how a new filter should be inserted  Parameter ``params``:     Parameters of the filter to be inserted
method
setProfilePreset(self, arg0: ...)
Set preset mode for ImageFiltersConfig.  Parameter ``presetMode``:     Preset mode for ImageFiltersConfig.
method
updateFilterAtIndex(self, index: int, params: ...|...|...|...) -> ImageFiltersConfig: ImageFiltersConfig
Insert filter parameters describing how a filter at index index should be updated  Parameter ``index``:     Index of the filter to be inserted  Parameter ``params``:     Parameters of the filter to be inserted
property
filterIndices
Index of the filter to be applied
method
property
filterParams
Parameters of the filter to be applied
method
class

depthai.ToFDepthConfidenceFilterConfig(depthai.Buffer)

method
method
setProfilePreset(self, arg0: ...)
Set preset mode for ImageFiltersPresetMode.  Parameter ``presetMode``:     Preset mode for ImageFiltersPresetMode.
property
confidenceThreshold
Threshold for the confidence filter
method
class

depthai.ImageAlignProperties

variable
property
alignHeight
Optional output height
method
property
alignWidth
Optional output width
method
property
interpolation
Interpolation type to use
method
property
numFramesPool
Num frames in output pool
method
property
numShaves
Number of shaves reserved.
method
property
outKeepAspectRatio
Whether to keep aspect ratio of the input or not
method
property
warpHwIds
Warp HW IDs to use, if empty, use auto/default
method
class

depthai.AlignProperties

class

depthai.RectificationProperties

class

depthai.GPUStereoProperties

class

depthai.VppProperties

property
initialConfig
Initial VPP configuration
method
property
numFramesPool
Number of frames in pool for output frames
method
class

depthai.ToFStereoFusionConfig

variable
variable
method
method
method
setCropToOverlap(self, enabled: bool) -> ToFStereoFusionConfig: ToFStereoFusionConfig
Enable cropping depth and confidence to the largest rectangle inside their geometric overlap. The overlap uses projection at infinity, independently of measured depth. Outputs retain native pixel resolution, with updated intrinsics and unchanged camera extrinsics.  Parameter ``enabled``:     Whether to crop the outputs. Disabled by default.  Returns:     This configuration for chaining. @note Set on initialConfig before starting     the pipeline. The crop is computed from the first synchronized input pair     and reused until either input transformation or dimensions change. If the     geometric overlap is empty, the node throws an error while processing that     pair.
class

depthai.VioConfig

variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
method
class

depthai.AssetManager

class

depthai.DeviceProperties

variable
variable
method
property
cameraSocketTuningBlobSize
Socket specific camera tuning blob size in bytes
method
property
cameraSocketTuningBlobUri
Socket specific camera tuning blob uri
method
property
cameraTuningBlobSize
Camera tuning blob size in bytes
method
property
cameraTuningBlobUri
Uri which points to camera tuning blob
method
property
sippBufferSize
SIPP (Signal Image Processing Pipeline) internal memory pool. SIPP is a framework used to schedule HW filters, e.g. ISP, Warp, Median filter etc. Changing the size of this pool is meant for advanced use cases, pushing the limits of the HW. By default memory is allocated in high speed CMX memory. Setting to 0 will allocate in DDR 256 kilobytes. Units are bytes.
method
property
sippDmaBufferSize
SIPP (Signal Image Processing Pipeline) internal DMA memory pool. SIPP is a framework used to schedule HW filters, e.g. ISP, Warp, Median filter etc. Changing the size of this pool is meant for advanced use cases, pushing the limits of the HW. Memory is allocated in high speed CMX memory Units are bytes.
method
property
xlinkChunkSize
Chunk size for splitting device-sent XLink packets, in bytes. A larger value could increase performance, with 0 disabling chunking. A negative value won't modify the device defaults - configured per protocol, currently 64*1024 for both USB and Ethernet.
method
class

depthai.Pipeline

class
AutoCalibrationMode
Members:    OFF    ON_START    CONTINUOUS
method
method
method
method
method
method
method
clearMultiDeviceCalibration(self)
Removes any cross-device calibration graph from the pipeline.  On a built pipeline the removal is pushed to all assigned devices, which then publish their local calibration metadata again.  Throws:     std::runtime_error when a device rejects the update
method
method
method
method
method
method
method
method
method
method
method
getDefaultDeviceProperties(self) -> DeviceProperties|None: DeviceProperties|None
Gets a copy of default device properties. If pipeline is in host only mode, returns host properties, otherwise returns device properties
method
method
method
getDeviceState(self, device: Device) -> DeviceState: DeviceState
Get the pipeline-level state of a device: RUNNING, DISCONNECTED, RECONNECTING or FAILED. Losing a device does not stop the pipeline (its streams go idle) unless it was the last device alive or a device consuming other devices' streams. See setStopOnDeviceLoss to stop on any device loss.
method
getDevices(self) -> list[Device]: list[Device]
Get all devices that are part of this pipeline - the default device (master) first, then the rest in registration order. Devices become part of the pipeline explicitly via addDevice or implicitly on first use by a node.
method
method
method
getGlobalProperties(self) -> GlobalProperties: GlobalProperties
Returns:     Global properties of current pipeline
method
getMultiDeviceCalibration(self) -> list[MultiDeviceExtrinsics]|None: list[MultiDeviceExtrinsics]|None
Gets the cross-device calibration graph from the pipeline  Returns:     the graph when one is set, std::nullopt otherwise
method
getNode(self, arg0: int) -> Node: Node
Get node with id if it exists, nullptr otherwise
method
method
getStopOnDeviceLoss(self) -> bool: bool
Get whether the pipeline stops when any device that runs a node is lost for good
method
method
method
method
method
remove(self, node: Node)
Removes a node from pipeline
method
method
serializeToJson(self, arg0: bool) -> json: json
Returns whole pipeline represented as JSON
method
method
method
method
method
method
method
setDeviceStateCallback(self, callback: typing.Callable[[Device, DeviceState], None])
Set a callback invoked on every device state transition. The callback is invoked from the affected device's monitor thread; do not block in it and do not call pipeline stop/start from it directly.
method
method
setMultiDeviceCalibration(self, graph: list[MultiDeviceExtrinsics])
Sets the cross-device calibration graph shared by all devices in the pipeline.  The graph is validated with beta::MultiDeviceCalibrationHandler. Before the pipeline is built it is only stored and travels to the devices with the pipeline schema. On a built pipeline it is additionally checked against every assigned device's local calibration and pushed to all assigned devices at runtime, so already streaming Camera and ToF nodes switch to the new graph.  Throws:     std::invalid_argument when the graph structure is invalid  Throws:     std::runtime_error when a device's local calibration does not match the     graph or a device rejects the update; devices updated before the failure are     restored to the previous graph and the pipeline keeps the previous graph  Parameter ``graph``:     Directed cross-device calibration edges.
method
method
method
setStopOnDeviceLoss(self, stop: bool)
Stop the pipeline when any device that runs a node is lost for good (strict mode). Off by default (permissive mode): the pipeline keeps running, the lost device's streams go idle and it stops only when the last device alive or a device consuming other devices' streams is lost.  A device is lost for good when its state becomes FAILED - after the reconnection attempts are exhausted. To stop as soon as a device disconnects, disable reconnection on the devices (Device::setMaxReconnectionAttempts(0)). Can be changed while the pipeline runs.  Parameter ``stop``:     True to stop the pipeline on any device loss
method
method
method
method
class

depthai.DeviceInfo

class

depthai.CrashDump

variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
static method
CrashDump.fromBytes(bytes: bytes) -> CrashDump: CrashDump
Deserialize the crash dump from a byte array (bytes in filesystem after calling toBytes)  Parameter ``bytes``:     Byte array  Returns:     Unique pointer to the appropriate CrashDump subclass
static method
CrashDump.load(tarPath: os.PathLike) -> CrashDump: CrashDump
Factory method to create a CrashDump from a tar file  Parameter ``tarPath``:     Path to the tar file  Returns:     Unique pointer to the CrashDump instance
method
method
method
method
method
method
fromTar(self, tarPath: os.PathLike)
Deserialize the crash dump from a tar file  Parameter ``tarPath``:     Path to the input tar file
method
getCrashDumpVersion(self) -> str: str
Get the version of the crash dump format  Returns:     Version string
method
getPlatform(self) -> Platform: Platform
Identify the platform that this crashdump corresponds to  Returns:     Platform enum value
method
toBytes(self) -> bytes: bytes
Serialize the crash dump to a byte array (bytes in filesystem after calling toTar)  Returns:     Byte array
method
toTar(self, tarPath: os.PathLike)
Serialize the crash dump to a tar file  Parameter ``tarPath``:     Path to the output tar file
class

depthai.CrashDumpRVC2.CrashReportCollection

class

depthai.CrashDumpRVC2.CrashReport

class
class
variable
variable
variable
variable
variable
method
property
prints
Device print/log lines captured around the crash.
method
property
statusFlags
Platform-specific crash/status flags captured with the report.
method
property
timerRaw
Raw device timer value captured in the crash report.
method
property
uptimeNs
Device uptime in nanoseconds at crash-report capture time.
method
class

depthai.CrashDumpRVC2.CrashReport.ErrorSourceInfo.AssertContext

class

depthai.CrashDumpRVC2.CrashReport.ErrorSourceInfo.TrapContext

class

depthai.CrashDumpRVC2.CrashReport.ThreadCallstack.CallstackContext

class

depthai.CrashDumpRVC4(depthai.CrashDump)

class

depthai.DeviceBase

static method
DeviceBase.getAllAvailableDevices() -> list[DeviceInfo]: list[DeviceInfo]
Returns all available devices  Returns:     Vector of available devices
static method
DeviceBase.getAllConnectedDevices() -> list[DeviceInfo]: list[DeviceInfo]
Returns information of all connected devices. The devices could be both connectable as well as already connected to devices.  Returns:     Vector of connected device information
static method
static method
DeviceBase.getDeviceById(deviceId: str) -> tuple[bool, DeviceInfo]: tuple[bool, DeviceInfo]
Finds a device by Device ID. Example: 14442C10D13EABCE00  Parameter ``deviceId``:     Device ID which uniquely specifies a device  Returns:     Tuple of bool and DeviceInfo. Bool specifies if device was found. DeviceInfo     specifies the found device
static method
DeviceBase.getDeviceByIdOrName(deviceIdOrName: str) -> tuple[bool, DeviceInfo]: tuple[bool, DeviceInfo]
Resolves a device from an IP address, name, or device ID without connecting to it.  Parameter ``deviceIdOrName``:     IP address, name, or device ID of the target device  Returns:     Tuple of bool and DeviceInfo. Bool specifies if device was found. DeviceInfo     specifies the found device
static method
static method
DeviceBase.getFirstAvailableDevice(skipInvalidDevices: bool = True) -> tuple[bool, DeviceInfo]: tuple[bool, DeviceInfo]
Gets first available device. Device can be either in XLINK_UNBOOTED or XLINK_BOOTLOADER state  Returns:     Tuple of bool and DeviceInfo. Bool specifies if device was found. DeviceInfo     specifies the found device
static method
DeviceBase.getGlobalProfilingData() -> ProfilingData: ProfilingData
Get current global accumulated profiling data  Returns:     ProfilingData from all devices
static method
DeviceBase.isInSetupMode(deviceIdOrName: str) -> bool|None: bool|None
Resolves a device from an IP address, name, or device ID without connecting to it and returns whether the resolved device is in setup mode.  Parameter ``deviceIdOrName``:     IP address, name, or device ID of the target device  Returns:     std::nullopt if the device could not be resolved, otherwise true if the     resolved device is in X_LINK_GATE_SETUP state and false otherwise
static method
DeviceBase.performHealthCheck(deviceInfo: DeviceInfo, config: HealthCheckConfig = ...) -> HealthCheckMetrics: HealthCheckMetrics
Performs a device health check.  The function connects to the supplied device, gathers device properties, and runs a short diagnostic pipeline for the checks enabled in the config.  Parameter ``devInfo``:     DeviceInfo which specifies which device to check  Parameter ``config``:     Health-check steps to execute  Returns:     HealthCheckMetrics with per-check pass/fail status and measured values
method
method
method
method
addLogCallback(self, callback: typing.Callable[[LogMessage], None]) -> int: int
Add a callback for device logging. The callback will be called from a separate thread with the LogMessage being passed.  Parameter ``callback``:     Callback to call whenever a log message arrives  Returns:     Id which can be used to later remove the callback
method
close(self)
Closes the connection to device. Better alternative is the usage of context manager: `with depthai.Device(pipeline) as device:`
method
crashDevice(self)
Crashes the device $.. warning::  ONLY FOR TESTING PURPOSES, it causes an unrecoverable crash on the device
method
factoryResetCBACalibration(self, camSocket: CameraBoardSocket)
Factory reset EEPROM data of the CBA if factory backup is available.  Parameter ``camSocket``:     CameraBoardSocket of the CBA (Camera Board Assembly)  Throws:     std::runtime_error If factory reset was unsuccessful $.. warning::  Experimental feature. This API might change or be removed in a future release.
method
factoryResetCalibration(self)
Factory reset EEPROM data if factory backup is available.  Throws:     std::runtime_error If factory reset was unsuccessful
method
flashCBACalibration(self, calibrationDataHandler: CBACalibrationHandler, camSocket: CameraBoardSocket)
Stores the Calibration and Device information to the CBA EEPROM  Throws:     std::runtime_error if failed to flash the calibration  Parameter ``calibrationObj``:     CBACalibrationHandler object which is loaded with calibration information.  Parameter ``camSocket``:     CameraBoardSocket of the CBA (Camera Board Assembly) $.. warning::  Experimental feature. This API might change or be removed in a future release.
method
flashCBAEepromClear(self, camSocket: CameraBoardSocket)
Destructive action, deletes User area EEPROM contents on CBA Requires PROTECTED permissions  Parameter ``camSocket``:     CameraBoardSocket of the CBA (Camera Board Assembly)  Throws:     std::runtime_error if failed to flash the calibration $.. warning::  Experimental feature. This API might change or be removed in a future release.  Returns:     True on successful flash, false on failure
method
flashCalibration(self, arg0: CalibrationHandler)
Stores the Calibration and Device information to the Device EEPROM  Throws:     std::runtime_error if failed to flash the calibration  Parameter ``calibrationObj``:     CalibrationHandler object which is loaded with calibration information.
method
flashEepromClear(self)
Destructive action, deletes User area EEPROM contents Requires PROTECTED permissions  Throws:     std::runtime_error if failed to flash the calibration  Returns:     True on successful flash, false on failure
method
flashFactoryCBACalibration(self, calibrationHandler: CBACalibrationHandler, camSocket: CameraBoardSocket)
Stores the Calibration and Device information to the CBA EEPROM in Factory area To perform this action, correct env variable must be set  Parameter ``calibrationHandler``:     CBACalibrationHandler  Parameter ``camSocket``:     CameraBoardSocket of the CBA (Camera Board Assembly)  Throws:     std::runtime_error if failed to flash the calibration $.. warning::  Experimental feature. This API might change or be removed in a future release.  Returns:     True on successful flash, false on failure
method
flashFactoryCBAEepromClear(self, camSocket: CameraBoardSocket)
Destructive action, deletes Factory area EEPROM contents on CBA Requires FACTORY PROTECTED permissions  Parameter ``camSocket``:     CameraBoardSocket of the CBA (Camera Board Assembly)  Throws:     std::runtime_error if failed to flash the calibration $.. warning::  Experimental feature. This API might change or be removed in a future release.  Returns:     True on successful flash, false on failure
method
flashFactoryCalibration(self, arg0: CalibrationHandler)
Stores the Calibration and Device information to the Device EEPROM in Factory area To perform this action, correct env variable must be set  Throws:     std::runtime_error if failed to flash the calibration  Returns:     True on successful flash, false on failure
method
flashFactoryEepromClear(self)
Destructive action, deletes Factory area EEPROM contents Requires FACTORY PROTECTED permissions  Throws:     std::runtime_error if failed to flash the calibration  Returns:     True on successful flash, false on failure
method
getAvailableStereoPairs(self) -> list[StereoPair]: list[StereoPair]
Get stereo pairs taking into account the calibration and connected cameras.  @note This method will always return a subset of `getStereoPairs`.  Returns:     Vector of stereo pairs
method
getBootloaderVersion(self) -> Version|None: Version|None
Gets Bootloader version if it was booted through Bootloader  Returns:     DeviceBootloader::Version if booted through Bootloader or none otherwise
method
getCalibration(self) -> CalibrationHandler: CalibrationHandler
Retrieves the CalibrationHandler object containing the non-persistent calibration  Throws:     std::runtime_error if failed to get the calibration  Returns:     The CalibrationHandler object containing the non-persistent calibration
method
getCameraSensorNames(self) -> dict[CameraBoardSocket, str]: dict[CameraBoardSocket, str]
Get sensor names for cameras that are connected to the device  Returns:     Map/dictionary with camera sensor names, indexed by socket
method
getChipTemperature(self) -> ChipTemperature: ChipTemperature
Retrieves current chip temperature as measured by device  Returns:     Temperature of various onboard sensors
method
getCmxMemoryUsage(self) -> MemoryInfo: MemoryInfo
Retrieves current CMX memory information from device  Returns:     Used, remaining and total cmx memory
method
getConnectedCameraFeatures(self) -> list[CameraFeatures]: list[CameraFeatures]
Get cameras that are connected to the device with their features/properties  Returns:     Vector of connected camera features
method
method
getConnectedIMU(self) -> str: str
Get connected IMU type  Returns:     IMU type
method
getConnectionInterfaces(self) -> list[connectionInterface]: list[connectionInterface]
Get connection interfaces for device  Returns:     Vector of connection type
method
getCrashDump(self, clearCrashDump: bool = True) -> CrashDump: CrashDump
Retrieves crash dump for debugging.  Parameter ``clearCrashDump``:     Clear the cached crash dump on device after collection  Returns:     Unique pointer to the CrashDump. Platform-specific crash dump payload may be     empty if no crash dump is available.
method
getDdrMemoryUsage(self) -> MemoryInfo: MemoryInfo
Retrieves current DDR memory information from device  Returns:     Used, remaining and total ddr memory
method
getDeviceId(self) -> str: str
Get DeviceId of device  Returns:     DeviceId of connected device
method
getDeviceInfo(self) -> DeviceInfo: DeviceInfo
Get the Device Info object o the device which is currently running  Returns:     DeviceInfo of the current device in execution
method
getDeviceName(self) -> typing.Any: typing.Any
Get device name if available  Returns:     device name or empty string if not available
method
getDeviceState(self) -> DeviceState: DeviceState
State of this device from the point of view of the pipeline it belongs to: RUNNING while connected, DISCONNECTED / RECONNECTING while a lost connection is being re-established and FAILED once it is gone for good. RUNNING for a device that is not part of a pipeline. Safe to call from any thread, including node threads.
method
getEmbeddedIMUFirmwareVersion(self) -> Version: Version
Get embedded IMU firmware version to which IMU can be upgraded  Returns:     Get embedded IMU firmware version to which IMU can be upgraded.
method
getExternalFrameSyncRole(self) -> ExternalFrameSyncRole: ExternalFrameSyncRole
Gets external frame sync role for the device  Returns:     Gets external frame sync role
method
getIMUFirmwareUpdateStatus(self) -> tuple[bool, float]: tuple[bool, float]
Get IMU firmware update status  Returns:     Whether IMU firmware update is done and last firmware update progress as     percentage. return value true and 100 means that the update was successful     return value true and other than 100 means that the update failed
method
getIMUFirmwareVersion(self) -> Version: Version
Get connected IMU firmware version  Returns:     IMU firmware version
method
getIrDrivers(self) -> list[tuple[str, int, int]]: list[tuple[str, int, int]]
Retrieves detected IR laser/LED drivers.  Returns:     Vector of tuples containing: driver name, I2C bus, I2C address. For OAK-D-     Pro it should be `[{"LM3644", 2, 0x63}]`
method
getLeonCssCpuUsage(self) -> CpuUsage: CpuUsage
Retrieves average CSS Leon CPU usage  Returns:     Average CPU usage and sampling duration
method
getLeonCssHeapUsage(self) -> MemoryInfo: MemoryInfo
Retrieves current CSS Leon CPU heap information from device  Returns:     Used, remaining and total heap memory
method
getLeonMssCpuUsage(self) -> CpuUsage: CpuUsage
Retrieves average MSS Leon CPU usage  Returns:     Average CPU usage and sampling duration
method
getLeonMssHeapUsage(self) -> MemoryInfo: MemoryInfo
Retrieves current MSS Leon CPU heap information from device  Returns:     Used, remaining and total heap memory
method
getLogLevel(self) -> LogLevel: LogLevel
Gets current logging severity level of the device.  Returns:     Logging severity level
method
getLogOutputLevel(self) -> LogLevel: LogLevel
Gets logging level which decides printing level to standard output.  Returns:     Standard output printing severity
method
getMxId(self) -> str: str
Get MxId of device  Returns:     MxId of connected device
method
getOSVersion(self) -> str: str
Gets device OS version if supported by the connected device.  Returns:     OS version string, for example "1.32.0"
method
getPlatform(self) -> Platform: Platform
Get the platform of the connected device  Returns:     Platform Platform enum
method
getPlatformAsString(self) -> str: str
Get the platform of the connected device as string  Returns:     std::string String representation of Platform
method
getProcessMemoryUsage(self) -> int: int
Retrieves current Rss memory usage of the device process  Returns:     Current Rss memory used
method
getProductName(self) -> typing.Any: typing.Any
Get product name if available  Returns:     product name or empty string if not available
method
getProfilingData(self) -> ProfilingData: ProfilingData
Get current accumulated profiling data  Returns:     ProfilingData from the specific device
method
getProperties(self) -> DeviceProperties: DeviceProperties
Gets current properties set on the device. Some properties might be not supported by the device, in that case they will have default values.  Returns:     DeviceProperties struct with current device properties
method
getState(self) -> CrashDump: CrashDump
Retrieves current device state in a crash dump format. It halts the device temporarily and might affect the running pipeline, it's best to close the device after this operation. Supported only on RVC2.
method
getStereoPairs(self) -> list[StereoPair]: list[StereoPair]
Get stereo pairs based on the device type.  Returns:     Vector of stereo pairs
method
getSupportedDeviceModels(self) -> list[DeviceModelZoo]: list[DeviceModelZoo]
Returns the subset of device zoo models currently available on the device.  Returns:     Supported device zoo models
method
getSystemInformationLoggingRate(self) -> float: float
Gets current rate of system information logging ("info" severity) in Hz.  Returns:     Logging rate in Hz
method
getUsbSpeed(self) -> UsbSpeed: UsbSpeed
Retrieves USB connection speed  Returns:     USB connection speed of connected device if applicable. Unknown otherwise.
method
getXLinkChunkSize(self) -> int: int
Gets current XLink chunk size.  Returns:     XLink chunk size in bytes
method
hasCrashDump(self) -> bool: bool
Retrieves whether the is crash dump stored on device or not.
method
hasCrashed(self) -> bool: bool
Check if the device has crashed  Returns:     True if the device has crashed (watchdog timeout detected), false otherwise
method
hasGPU(self) -> bool: bool
Checks if a GPU is available on the device.  @note This is only meaningful on RVC4 platforms.  Returns:     True if supported, false otherwise
method
isCBAEepromAvailable(self, camSocket: CameraBoardSocket) -> bool: bool
Check if EEPROM is available for a given CBA  Parameter ``camSocket``:     CameraBoardSocket of the CBA (Camera Board Assembly)  .. warning::     Experimental feature. This API might change or be removed in a future     release.  Returns:     True if EEPROM is present on board, false otherwise
method
isClosed(self) -> bool: bool
Is the device already closed (or disconnected)  .. warning::     This function is thread-unsafe and may return outdated incorrect values. It     is only meant for use in simple single-threaded code. Well written code     should handle exceptions when calling any DepthAI apis to handle hardware     events and multithreaded use.
method
isEepromAvailable(self) -> bool: bool
Check if EEPROM is available  Returns:     True if EEPROM is present on board, false otherwise
method
isGpuStereoSupported(self) -> bool: bool
Checks if GPUStereo is supported on the device.  @note This is only meaningful on RVC4 platforms.  Returns:     True if supported, false otherwise
method
isNeuralDepthSupported(self) -> bool: bool
Checks if Neural Depth is supported on the device  Returns:     True if supported, false otherwise
method
isPipelineRunning(self) -> bool: bool
Checks if devices pipeline is already running  Returns:     True if running, false otherwise
method
readCBACalibration(self, camSocket: CameraBoardSocket) -> CBACalibrationHandler: CBACalibrationHandler
Fetches the EEPROM data from the CBA and loads it into CalibrationHandler object If no calibration is flashed, it returns default @note This reads EEPROM contents directly and does not merge calibration data from other sources.  Parameter ``camSocket``:     CameraBoardSocket of the CBA (Camera Board Assembly)  .. warning::     Experimental feature. This API might change or be removed in a future     release.  Returns:     The CalibrationHandler object containing the calibration currently flashed     on CBA EEPROM
method
readCBACalibration2(self, camSocket: CameraBoardSocket) -> CBACalibrationHandler: CBACalibrationHandler
Fetches the EEPROM data from the CBA and loads it into CalibrationHandler object @note This reads EEPROM contents directly and does not merge calibration data from other sources.  Parameter ``camSocket``:     CameraBoardSocket of the CBA (Camera Board Assembly)  Throws:     std::runtime_error if no calibration is flashed $.. warning::  Experimental feature. This API might change or be removed in a future release.  Returns:     The CalibrationHandler object containing the calibration currently flashed     on CBA EEPROM
method
readCBACalibrationOrDefault(self, camSocket: CameraBoardSocket) -> CBACalibrationHandler: CBACalibrationHandler
Fetches the EEPROM data from the CBA and loads it into CalibrationHandler object If no calibration is flashed, it returns default @note This reads EEPROM contents directly and does not merge calibration data from other sources.  Parameter ``camSocket``:     CameraBoardSocket of the CBA (Camera Board Assembly)  .. warning::     Experimental feature. This API might change or be removed in a future     release.  Returns:     The CalibrationHandler object containing the calibration currently flashed     on CBA EEPROM
method
readCalibration(self) -> CalibrationHandler: CalibrationHandler
Fetches the EEPROM data from the device and loads it into CalibrationHandler object If no calibration is flashed, it returns default @note This reads EEPROM contents directly and does not merge calibration data from other sources.  Returns:     The CalibrationHandler object containing the calibration currently flashed     on device EEPROM
method
readCalibration2(self) -> CalibrationHandler: CalibrationHandler
Fetches the EEPROM data from the device and loads it into CalibrationHandler object @note This reads EEPROM contents directly and does not merge calibration data from other sources.  Throws:     std::runtime_error if no calibration is flashed  Returns:     The CalibrationHandler object containing the calibration currently flashed     on device EEPROM
method
readCalibrationOrDefault(self) -> CalibrationHandler: CalibrationHandler
Fetches the EEPROM data from the device and loads it into CalibrationHandler object If no calibration is flashed, it returns default @note This reads EEPROM contents directly and does not merge calibration data from other sources.  Returns:     The CalibrationHandler object containing the calibration currently flashed     on device EEPROM
method
readCalibrationRaw(self) -> bytes: bytes
Fetches the raw EEPROM data from User area  Throws:     std::runtime_error if any error occurred  Returns:     Binary dump of User area EEPROM data
method
readCcmEepromRaw(self, socket: CameraBoardSocket, size: int, offset: int = 0) -> bytes: bytes
Fetches the raw EEPROM data from the specified CCM (compact camera module). Note: only certain CCMs (e.g. ToF) do have an EEPROM chip on-module  Parameter ``socket``:     CameraBoardSocket where the CCM is placed  Parameter ``size``:     Size in bytes to read  Parameter ``offset``:     Absolute offset in EEPROM memory to read from  Throws:     std::runtime_exception if any error occurred  Returns:     Binary dump of EEPROM data
method
readFactoryCBACalibration(self, camSocket: CameraBoardSocket) -> CBACalibrationHandler: CBACalibrationHandler
Fetches the CBA EEPROM data from Factory area and loads it into CalibrationHandler object  Parameter ``camSocket``:     CameraBoardSocket of the CBA (Camera Board Assembly)  Throws:     std::runtime_error if no calibration is flashed $.. warning::  Experimental feature. This API might change or be removed in a future release.  Returns:     The CalibrationHandler object containing the calibration currently flashed     on CBA EEPROM in Factory Area
method
readFactoryCBACalibrationOrDefault(self, camSocket: CameraBoardSocket) -> CBACalibrationHandler: CBACalibrationHandler
Fetches the CBA EEPROM data from Factory area and loads it into CalibrationHandler object If no calibration is flashed, it returns default  Parameter ``camSocket``:     CameraBoardSocket of the CBA (Camera Board Assembly)  .. warning::     Experimental feature. This API might change or be removed in a future     release.  Returns:     The CalibrationHandler object containing the calibration currently flashed     on CBA EEPROM in Factory Area
method
readFactoryCalibration(self) -> CalibrationHandler: CalibrationHandler
Fetches the EEPROM data from Factory area and loads it into CalibrationHandler object  Throws:     std::runtime_error if no calibration is flashed  Returns:     The CalibrationHandler object containing the calibration currently flashed     on device EEPROM in Factory Area
method
readFactoryCalibrationOrDefault(self) -> CalibrationHandler: CalibrationHandler
Fetches the EEPROM data from Factory area and loads it into CalibrationHandler object If no calibration is flashed, it returns default  Returns:     The CalibrationHandler object containing the calibration currently flashed     on device EEPROM in Factory Area
method
readFactoryCalibrationRaw(self) -> bytes: bytes
Fetches the raw EEPROM data from Factory area  Throws:     std::runtime_error if any error occurred  Returns:     Binary dump of Factory area EEPROM data
method
registerCrashdumpCallback(self, callback: typing.Callable[[CrashDump], None])
Register a callback that will be called when the device crashes. The callback receives a shared pointer to the CrashDump, which can be modified before it is stored. Only one callback can be registered at a time.  Parameter ``callback``:     Callback to call when a crash dump is collected
method
removeCrashdumpCallback(self)
Removes the registered crash dump callback
method
removeLogCallback(self, callbackId: int) -> bool: bool
Removes a callback  Parameter ``callbackId``:     Id of callback to be removed  Returns:     True if callback was removed, false otherwise
method
setCalibration(self, arg0: CalibrationHandler)
Sets the Calibration at runtime. This is not persistent and will be lost after device reset.  Throws:     std::runtime_error if failed to set the calibration  Parameter ``calibrationObj``:     CalibrationHandler object which is loaded with calibration information.
method
setExternalFrameSyncRole(self, role: ExternalFrameSyncRole) -> tuple[bool, str]: tuple[bool, str]
Sets external frame sync role for the device  Parameter ``role``:     External frame sync role to be set, AUTO_DETECT by default  Returns:     Tuple of bool and string. Bool specifies if role was set without failures.     String is the error message describing the failure reason.
method
method
setExternalStrobeRelativeLimits(self, min: float, max: float) -> tuple[bool, str]: tuple[bool, str]
Sets the relative external strobe limits. Limits the strobe duty cycle, between 0 and 1, as a fraction of the whole period. 0 means always off, 1 means always on. The rising edge of the strobe signal is always synced to end of exposure. The falling edge of the strobe signal is then limited according to the min and max values. Default values are 0.005 and 0.995  Parameter ``min``:     Minimum strobe value  Parameter ``max``:     Maximum strobe value  Returns:     Tuple of bool and string. Bool specifies if role was set without failures.     String is the error message describing the failure reason.
method
setIrFloodLightIntensity(self, intensity: float, mask: int = -1) -> bool: bool
Sets the intensity of the IR Flood Light. Limits: Intensity is directly normalized to 0 - 1500mA current. The duty cycle is 30% when exposure time is longer than 30% frame time. Otherwise, duty cycle is 100% of exposure time. The duty cycle is controlled by the `left` camera STROBE, aligned to start of exposure. The emitter is turned off by default  Parameter ``intensity``:     Intensity on range 0 to 1, that will determine brightness, 0 or negative to     turn off  Parameter ``mask``:     Optional mask to modify only Left (0x1) or Right (0x2) sides on OAK-D-Pro-W-     DEV  Returns:     True on success, false if not found or other failure
method
setIrLaserDotProjectorIntensity(self, intensity: float, mask: int = -1) -> bool: bool
Sets the intensity of the IR Laser Dot Projector. Limits: up to 765mA at 30% frame time duty cycle when exposure time is longer than 30% frame time. Otherwise, duty cycle is 100% of exposure time, with current increased up to max 1200mA to make up for shorter duty cycle. The duty cycle is controlled by `left` camera STROBE, aligned to start of exposure. The emitter is turned off by default  Parameter ``intensity``:     Intensity on range 0 to 1, that will determine brightness. 0 or negative to     turn off  Parameter ``mask``:     Optional mask to modify only Left (0x1) or Right (0x2) sides on OAK-D-Pro-W-     DEV  Returns:     True on success, false if not found or other failure
method
setLogLevel(self, level: LogLevel)
Sets the devices logging severity level. This level affects which logs are transferred from device to host.  Parameter ``level``:     Logging severity
method
setLogOutputLevel(self, level: LogLevel)
Sets logging level which decides printing level to standard output. If lower than setLogLevel, no messages will be printed  Parameter ``level``:     Standard output printing severity
method
setMaxReconnectionAttempts(self, maxAttempts: int, callback: typing.Callable[[Device.ReconnectionStatus], None] = None)
Sets max number of automatic reconnection attempts  Parameter ``maxAttempts``:     Maximum number of reconnection attempts, 0 to disable reconnection  Parameter ``callBack``:     Callback to be called when reconnection is attempted
method
setMultiDeviceCalibration(self, graph: list[MultiDeviceExtrinsics]|None)
Sets the cross-device calibration graph at runtime. This is not persistent and will be lost after device reset. The device re-validates the graph against its local calibration before applying it.  Throws:     std::runtime_error if the device rejects the graph  Parameter ``graph``:     Cross-device calibration edges, or std::nullopt to remove the graph
method
setProperties(self, properties: DeviceProperties)
Sets properties for the device.  Parameter ``properties``:     DeviceProperties struct with properties to set. Only properties which are     supported by the device and have different values than current ones will be     applied. Some properties are only applied before starting the pipeline.
method
setSippBufferSize(self, sizeBytes: int)
Sets the size of the SIPP buffer on the device.  Parameter ``sizeBytes``:     SIPP buffer size in bytes. Device default is 18 * 1024 bytes
method
setSippDmaBufferSize(self, sizeBytes: int)
Sets the size of the SIPP DMA buffer on the device.  Parameter ``sizeBytes``:     SIPP DMA buffer size in bytes. Device default is 16 * 1024 bytes
method
setSystemInformationLoggingRate(self, rateHz: float)
Sets rate of system information logging ("info" severity). Default 1Hz If parameter is less or equal to zero, then system information logging will be disabled  Parameter ``rateHz``:     Logging rate in Hz
method
method
setXLinkChunkSize(self, sizeBytes: int)
Sets the chunk size for splitting device-sent XLink packets. A larger value could increase performance, and 0 disables chunking. A negative value is ignored. Device defaults are configured per protocol, currently 64*1024 for both USB and Ethernet.  Parameter ``sizeBytes``:     XLink chunk size in bytes
method
setXLinkRateLimit(self, maxRateBytesPerSecond: int, burstSize: int = 0, waitUs: int = 0)
Sets the maximum transmission rate for the XLink connection on device side, using a simple token bucket algorithm. Useful for bandwidth throttling  Parameter ``maxRateBytesPerSecond``:     Rate limit in Bytes/second  Parameter ``burstSize``:     Size in Bytes for how much to attempt to send once, 0 = auto  Parameter ``waitUs``:     Time in microseconds to wait for replenishing tokens, 0 = auto
method
startIMUFirmwareUpdate(self, forceUpdate: bool = False) -> bool: bool
Starts IMU firmware update asynchronously only if IMU node is not running. If current firmware version is the same as embedded firmware version then it's no- op. Can be overridden by forceUpdate parameter. State of firmware update can be monitored using getIMUFirmwareUpdateStatus API.  Parameter ``forceUpdate``:     Force firmware update or not. Will perform FW update regardless of current     version and embedded firmware version.  Returns:     Returns whether firmware update can be started. Returns false if IMU node is     started.
method
tryFlashCBACalibration(self, calibrationDataHandler: CBACalibrationHandler, camSocket: CameraBoardSocket) -> bool: bool
Stores the Calibration and Device information to the CBA EEPROM  Parameter ``calibrationObj``:     CBACalibrationHandler object which is loaded with calibration information.  Parameter ``camSocket``:     CameraBoardSocket of the CBA (Camera Board Assembly)  .. warning::     Experimental feature. This API might change or be removed in a future     release.  Returns:     true on successful flash, false on failure
method
tryFlashCalibration(self, calibrationDataHandler: CalibrationHandler) -> bool: bool
Stores the Calibration and Device information to the Device EEPROM  Parameter ``calibrationObj``:     CalibrationHandler object which is loaded with calibration information.  Returns:     true on successful flash, false on failure
method
writeCcmEepromRaw(self, socket: CameraBoardSocket, data: bytes, offset: int = 0)
Writes the raw EEPROM data from the specified CCM (compact camera module). Note: only certain CCMs (e.g. ToF) do have an EEPROM chip on-module Requires FACTORY PROTECTED permissions  Parameter ``socket``:     CameraBoardSocket where the CCM is placed  Parameter ``data``:     Data buffer to write  Parameter ``offset``:     Absolute offset in EEPROM memory to read from  Throws:     std::runtime_exception if any error occurred
class

depthai.BoardConfig

class
USB
USB related config
class
Network
Network configuration
class
GPIO
GPIO config
class
UART
UART instance config
class
UVC
UVC configuration for USB descriptor
class
class
class
class
class
variable
variable
variable
variable
variable
method
property
emmc
eMMC config
method
property
logDevicePrints
log device prints
method
property
logPath
log path
method
property
logSizeMax
Max log size
method
property
logVerbosity
log verbosity
method
property
mipi4LaneRgb
MIPI 4Lane RGB config
method
property
method
property
sysctl
Optional list of FreeBSD sysctl parameters to be set (system, network, etc.). For example: "net.inet.tcp.delayed_ack=0" (this one is also set by default)
method
property
uart
UART instance map
method
property
usb3PhyInternalClock
USB3 phy config
method
property
watchdogTimeoutMs
Watchdog config
method
class

depthai.BoardConfig.USB

class

depthai.BoardConfig.Network

class

depthai.BoardConfig.GPIO

class
Mode
Members:    ALT_MODE_0 :     ALT_MODE_1 :     ALT_MODE_2 :     ALT_MODE_3 :     ALT_MODE_4 :     ALT_MODE_5 :     ALT_MODE_6 :     DIRECT : 
class
Direction
Members:    INPUT :     OUTPUT : 
class
Level
Members:    LOW :     HIGH : 
class
Pull
Members:    NO_PULL :     PULL_UP :     PULL_DOWN :     BUS_KEEPER : 
class
Drive
Drive strength in mA (2, 4, 8 and 12mA)  Members:    MA_2 :     MA_4 :     MA_8 :     MA_12 : 
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
variable
method
class

depthai.BoardConfig.UART

class

depthai.DeviceBootloader

class
Type
Members:    AUTO    USB    NETWORK
class
Memory
Members:    AUTO    FLASH    EMMC
class
Section
Members:    AUTO    HEADER    BOOTLOADER    BOOTLOADER_CONFIG    APPLICATION
class
class
class
class
class
static method
DeviceBootloader.getAllAvailableDevices() -> list[DeviceInfo]: list[DeviceInfo]
Searches for connected devices in either UNBOOTED or BOOTLOADER states.  Returns:     Vector of all found devices
static method
static method
static method
DeviceBootloader.getFirstAvailableDevice() -> tuple[bool, DeviceInfo]: tuple[bool, DeviceInfo]
Searches for connected devices in either UNBOOTED or BOOTLOADER states and returns first available.  Returns:     Tuple of boolean and DeviceInfo. If found boolean is true and DeviceInfo     describes the device. Otherwise false
method
method
method
method
bootMemory(self, fw: ..., std: ...)
Boots a custom FW in memory  Parameter ``fw``:     $Throws:  A runtime exception if there are any communication issues
method
bootUsbRomBootloader(self)
Boots into integrated ROM bootloader in USB mode  Throws:     A runtime exception if there are any communication issues
method
close(self)
Closes the connection to device. Better alternative is the usage of context manager: `with depthai.DeviceBootloader(deviceInfo) as bootloader:`
method
flashBootHeader(self, memory: DeviceBootloader.Memory, frequency: int = -1, location: int = -1, dummyCycles: int = -1, offset: int = -1) -> tuple[bool, str]: tuple[bool, str]
Flash optimized boot header  Parameter ``memory``:     Which memory to flasht the header to  Parameter ``frequency``:     SPI specific parameter, frequency in MHz  Parameter ``location``:     Target location the header should boot to. Default to location of bootloader  Parameter ``dummyCycles``:     SPI specific parameter  Parameter ``offset``:     Offset in memory to flash the header to. Defaults to offset of boot header  Returns:     status as std::tuple<bool, std::string>
method
method
flashClear(self, memory: DeviceBootloader.Memory = ...) -> tuple[bool, str]: tuple[bool, str]
Clears flashed application on the device, by removing SBR boot structure Doesn't remove fast boot header capability to still boot the application
method
flashConfig(self, config: DeviceBootloader.Config, memory: DeviceBootloader.Memory = ..., type: DeviceBootloader.Type = ...) -> tuple[bool, str]: tuple[bool, str]
Flashes configuration to bootloader  Parameter ``configData``:     Configuration structure  Parameter ``memory``:     Optional - to which memory flash configuration  Parameter ``type``:     Optional - for which type of bootloader to flash configuration
method
flashConfigClear(self, memory: DeviceBootloader.Memory = ..., type: DeviceBootloader.Type = ...) -> tuple[bool, str]: tuple[bool, str]
Clears configuration data  Parameter ``memory``:     Optional - on which memory to clear configuration data  Parameter ``type``:     Optional - for which type of bootloader to clear configuration data
method
flashConfigData(self, configData: json, memory: DeviceBootloader.Memory = ..., type: DeviceBootloader.Type = ...) -> tuple[bool, str]: tuple[bool, str]
Flashes configuration data to bootloader  Parameter ``configData``:     Unstructured configuration data  Parameter ``memory``:     Optional - to which memory flash configuration  Parameter ``type``:     Optional - for which type of bootloader to flash configuration
method
flashConfigFile(self, configData: os.PathLike, memory: DeviceBootloader.Memory = ..., type: DeviceBootloader.Type = ...) -> tuple[bool, str]: tuple[bool, str]
Flashes configuration data to bootloader  Parameter ``configPath``:     Unstructured configuration data  Parameter ``memory``:     Optional - to which memory flash configuration  Parameter ``type``:     Optional - for which type of bootloader to flash configuration
method
method
flashFastBootHeader(self, memory: DeviceBootloader.Memory, frequency: int = -1, location: int = -1, dummyCycles: int = -1, offset: int = -1) -> tuple[bool, str]: tuple[bool, str]
Flash fast boot header. Application must already be present in flash, or location must be specified manually. Note - Can soft brick your device if firmware location changes.  Parameter ``memory``:     Which memory to flash the header to  Parameter ``frequency``:     SPI specific parameter, frequency in MHz  Parameter ``location``:     Target location the header should boot to. Default to location of bootloader  Parameter ``dummyCycles``:     SPI specific parameter  Parameter ``offset``:     Offset in memory to flash the header to. Defaults to offset of boot header  Returns:     status as std::tuple<bool, std::string>
method
flashGpioModeBootHeader(self, memory: DeviceBootloader.Memory, mode: int) -> tuple[bool, str]: tuple[bool, str]
Flash boot header which boots same as equivalent GPIO mode would  Parameter ``gpioMode``:     GPIO mode equivalent
method
flashUsbRecoveryBootHeader(self, memory: DeviceBootloader.Memory) -> tuple[bool, str]: tuple[bool, str]
Flash USB recovery boot header. Switches to USB ROM Bootloader  Parameter ``memory``:     Which memory to flash the header to
method
flashUserBootloader(self, progressCallback: typing.Callable[[float], None], path: os.PathLike = '') -> tuple[bool, str]: tuple[bool, str]
Flashes user bootloader to the current board. Available for NETWORK bootloader type  Parameter ``progressCallback``:     Callback that sends back a value between 0..1 which signifies current     flashing progress  Parameter ``path``:     Optional parameter to custom bootloader to flash
method
getMemoryInfo(self, arg0: DeviceBootloader.Memory) -> DeviceBootloader.MemoryInfo: DeviceBootloader.MemoryInfo
Retrieves information about specified memory  Parameter ``memory``:     Specifies which memory to query
method
getType(self) -> DeviceBootloader.Type: DeviceBootloader.Type
Returns:     Type of currently connected bootloader
method
getVersion(self) -> Version: Version
Returns:     Version of current running bootloader
method
isAllowedFlashingBootloader(self) -> bool: bool
Returns:     True if allowed to flash bootloader
method
isEmbeddedVersion(self) -> bool: bool
Returns:     True when bootloader was booted using latest bootloader integrated in the     library. False when bootloader is already running on the device and just     connected to.
method
isUserBootloader(self) -> bool: bool
Retrieves whether current bootloader is User Bootloader (B out of A/B configuration)
method
isUserBootloaderSupported(self) -> bool: bool
Checks whether User Bootloader is supported with current bootloader  Returns:     true of User Bootloader is supported, false otherwise
method
readApplicationInfo(self, memory: DeviceBootloader.Memory) -> DeviceBootloader.ApplicationInfo: DeviceBootloader.ApplicationInfo
Reads information about flashed application in specified memory from device  Parameter ``memory``:     Specifies which memory to query
method
readConfig(self, memory: DeviceBootloader.Memory = ..., type: DeviceBootloader.Type = ...) -> DeviceBootloader.Config: DeviceBootloader.Config
Reads configuration from bootloader  Parameter ``memory``:     Optional - from which memory to read configuration  Parameter ``type``:     Optional - from which type of bootloader to read configuration  Returns:     Configuration structure
method
readConfigData(self, memory: DeviceBootloader.Memory = ..., type: DeviceBootloader.Type = ...) -> json: json
Reads configuration data from bootloader  Returns:     Unstructured configuration data  Parameter ``memory``:     Optional - from which memory to read configuration data  Parameter ``type``:     Optional - from which type of bootloader to read configuration data
method
class

depthai.DeviceBootloader.UsbConfig

class

depthai.DeviceBootloader.ApplicationInfo

class

depthai.DeviceBootloader.MemoryInfo

class

depthai.CalibrationHandler

static method
CalibrationHandler.fromJson(eepromDataJson: json, validateExtrinsics: bool|None = None) -> CalibrationHandler: CalibrationHandler
Construct a new Calibration Handler object from JSON EepromData.  Parameter ``eepromDataJson``:     EepromData as JSON  Parameter ``validateCalibration``:     Enable internal check for extrinsics cycling links or dangling references.
method
method
eepromToJson(self) -> json: json
Get JSON representation of calibration data  Returns:     JSON structure
method
eepromToJsonFile(self, destPath: os.PathLike) -> bool: bool
Write raw calibration/board data to json file.  Parameter ``destPath``:     Full path to the json file in which raw calibration data will be stored  Returns:     True on success, false otherwise
method
getAccelerometerCalibration(self) -> list[list[float]]: list[list[float]]
Get canonical accelerometer calibration matrix [Q|b].  The linear transform Q is dimensionless. The bias column b is stored in SI units of [m/s^2].  Returns:     returns 3x4 matrix in the form [[q00, q01, q02, b0], [q10, q11, q12, b1],     [q20, q21, q22, b2]]
method
getBaselineDistance(self, cam1: CameraBoardSocket = ..., cam2: CameraBoardSocket = ..., useSpecTranslation: bool = True, unit: LengthUnit = ...) -> float: float
Get the baseline distance between two specified cameras. By default it will get the baseline between CameraBoardSocket.RIGHT and CameraBoardSocket.LEFT.  Parameter ``cam1``:     First camera  Parameter ``cam2``:     Second camera  Parameter ``useSpecTranslation``:     Enabling this bool uses the translation information from the board design     data (not the calibration data)  Parameter ``unit``:     Units of the returned baseline distance (default: centimeters)  Returns:     baseline distance
method
getCameraExtrinsics(self, srcCamera: CameraBoardSocket, dstCamera: CameraBoardSocket, useSpecTranslation: bool = False, unit: LengthUnit = ...) -> list[list[float]]: list[list[float]]
Get the Camera Extrinsics object between two cameras from the calibration data if there is a linked connection between any two cameras then the relative rotation and translation is returned by this function.  Parameter ``srcCamera``:     Camera Id of the camera which will be considered as origin.  Parameter ``dstCamera``:     Camera Id of the destination camera to which we are fetching the rotation     and translation from the SrcCamera  Parameter ``useSpecTranslation``:     Enabling this bool uses the translation information from the board design     data  Parameter ``unit``:     Units of the returned translation (default: centimeters)  Returns:     a transformationMatrix which is 4x4 in homogeneous coordinate system  Matrix representation of transformation matrix \f[ \text{Transformation Matrix} = \left [ \begin{matrix} r_{00} & r_{01} & r_{02} & T_x \\ r_{10} & r_{11} & r_{12} & T_y \\ r_{20} & r_{21} & r_{22} & T_z \\ 0 & 0 & 0 & 1 \end{matrix} \right ] \f]
method
method
getCameraRotationMatrix(self, srcCamera: CameraBoardSocket, dstCamera: CameraBoardSocket) -> list[list[float]]: list[list[float]]
Get the Camera rotation matrix between two cameras from the calibration data.  Parameter ``srcCamera``:     Camera Id of the camera which will be considered as origin.  Parameter ``dstCamera``:     Camera Id of the destination camera to which we are fetching the rotation     vector from the SrcCamera  Returns:     a 3x3 rotation matrix Matrix representation of rotation matrix \f[     \text{Rotation Matrix} = \left [ \begin{matrix} r_{00} & r_{01} & r_{02}\\     r_{10} & r_{11} & r_{12}\\ r_{20} & r_{21} & r_{22}\\ \end{matrix} \right ]     \f]
method
getCameraToImuExtrinsics(self, cameraId: CameraBoardSocket, useSpecTranslation: bool = False, unit: LengthUnit = ...) -> list[list[float]]: list[list[float]]
Get the Camera To Imu Extrinsics object From the data loaded if there is a linked connection between IMU and the given camera then there relative rotation and translation from the camera to IMU is returned.  Parameter ``cameraId``:     Camera Id of the camera which will be considered as origin. from which     Transformation matrix to the IMU will be found  Parameter ``useSpecTranslation``:     Enabling this bool uses the translation information from the board design     data  Parameter ``unit``:     Units of the returned translation (default: centimeters)  Returns:     Returns a transformationMatrix which is 4x4 in homogeneous coordinate system  Matrix representation of transformation matrix \f[ \text{Transformation Matrix} = \left [ \begin{matrix} r_{00} & r_{01} & r_{02} & T_x \\ r_{10} & r_{11} & r_{12} & T_y \\ r_{20} & r_{21} & r_{22} & T_z \\ 0 & 0 & 0 & 1 \end{matrix} \right ] \f]
method
getCameraTranslationVector(self, srcCamera: CameraBoardSocket, dstCamera: CameraBoardSocket, useSpecTranslation: bool = True, unit: LengthUnit = ...) -> list[float]: list[float]
Get the Camera translation vector between two cameras from the calibration data.  Parameter ``srcCamera``:     Camera Id of the camera which will be considered as origin.  Parameter ``dstCamera``:     Camera Id of the destination camera to which we are fetching the translation     vector from the SrcCamera  Parameter ``useSpecTranslation``:     Disabling this bool uses the translation information from the calibration     data (not the board design data)  Parameter ``unit``:     Units of the returned translation (default: centimeters)  Returns:     a translation vector like [x, y, z]
method
getCameraWithLowestId(self) -> CameraBoardSocket: CameraBoardSocket
Get the lowest camera socket  Returns:     the lowest camera socket
method
getDefaultIntrinsics(self, cameraId: CameraBoardSocket) -> tuple[list[list[float]], int, int]: tuple[list[list[float]], int, int]
Get the Default Intrinsics object  Parameter ``cameraId``:     Uses the cameraId to identify which camera intrinsics to return  Returns:     Represents the 3x3 intrinsics matrix of the respective camera along with     width and height at which it was calibrated.  Matrix representation of intrinsic matrix \f[ \text{Intrinsic Matrix} = \left [ \begin{matrix} f_x & 0 & c_x \\ 0 & f_y & c_y \\ 0 & 0 & 1 \end{matrix} \right ] \f]
method
getDistortionCoefficients(self, cameraId: CameraBoardSocket) -> list[float]: list[float]
Get the Distortion Coefficients object  Parameter ``cameraId``:     Uses the cameraId to identify which distortion Coefficients to return.  Returns:     the distortion coefficients of the requested camera in this order:     [k1,k2,p1,p2,k3,k4,k5,k6,s1,s2,s3,s4,τx,τy] for CameraModel::Perspective or     [k1, k2, k3, k4] for CameraModel::Fisheye see     https://docs.opencv.org/4.5.4/d9/d0c/group__calib3d.html for Perspective     model (Rational Polynomial Model) see     https://docs.opencv.org/4.5.4/db/d58/group__calib3d__fisheye.html for     Fisheye model
method
getDistortionModel(self, cameraId: CameraBoardSocket) -> CameraModel: CameraModel
Get the distortion model of the given camera  Parameter ``cameraId``:     of the camera with lens position is requested.  Returns:     lens position of the camera with given cameraId at which it was calibrated.
method
getEepromData(self) -> EepromData: EepromData
Get the Eeprom Data object  Returns:     EepromData object which contains the raw calibration data
method
getFov(self, cameraId: CameraBoardSocket, useSpec: bool = True) -> float: float
Get the Fov of the camera  Parameter ``cameraId``:     of the camera of which we are fetching fov.  Parameter ``useSpec``:     Disabling this bool will calculate the fov based on intrinsics (focal     length, image width), instead of getting it from the camera specs  Returns:     field of view of the camera with given cameraId.
method
getGyroscopeCalibration(self) -> list[list[float]]: list[list[float]]
Get canonical gyroscope calibration matrix [Q|b].  The linear transform Q is dimensionless. The bias column b is stored in SI units of [rad/s].  Returns:     returns 3x4 matrix in the form [[q00, q01, q02, b0], [q10, q11, q12, b1],     [q20, q21, q22, b2]]
method
getHousingCalibration(self, srcCamera: CameraBoardSocket, housingCS: HousingCoordinateSystem, useSpecTranslation: bool = True, unit: LengthUnit = ...) -> list[list[float]]: list[list[float]]
Get the transformation matrix between a camera and a chosen housing coordinate system. The returned 4x4 homogeneous transformation matrix maps points from the camera's coordinate system into the specified housing coordinate system.  The transformation consists of a rotation matrix and translation vector extracted either from the calibration data or from the board design (specification) data, depending on the `useSpecTranslation` flag.  Parameter ``srcCamera``:     Camera whose coordinate frame will be treated as the origin.  Parameter ``housingCS``:     The housing coordinate system to which the camera transformation is     requested (e.g. VESA_RIGHT, FRONT_COVER_LEFT, etc.).  Parameter ``useSpecTranslation``:     If true, uses board-design (spec) translation values. If false, uses     calibrated translation values.  Parameter ``unit``:     Units of the returned translation (default: centimeters)  Returns:     A 4x4 homogeneous transformation matrix.  Matrix representation of the transformation: \f[ \text{Transformation Matrix} = \left[ \begin{matrix} r_{00} & r_{01} & r_{02} & T_x \\ r_{10} & r_{11} & r_{12} & T_y \\ r_{20} & r_{21} & r_{22} & T_z \\ 0 & 0 & 0 & 1 \end{matrix} \right] \f]
method
getImuNoiseParameters(self) -> ImuNoiseParameters: ImuNoiseParameters
Get complete IMU noise parameters.  Accelerometer noise terms are stored in [m/s^2]-based units. Gyroscope noise terms are stored in [rad/s]-based units.  Returns:     returns IMU noise parameters
method
getImuParameters(self) -> ImuCalibrationParams: ImuCalibrationParams
Get full IMU parameter payload.  Accelerometer calibration bias terms are stored in [m/s^2]. Gyroscope calibration bias terms are stored in [rad/s].  Returns:     returns IMU parameters containing noise + calibration matrices
method
getImuToCameraExtrinsics(self, cameraId: CameraBoardSocket, useSpecTranslation: bool = False, unit: LengthUnit = ...) -> list[list[float]]: list[list[float]]
Get the Imu To Camera Extrinsics object from the data loaded if there is a linked connection between IMU and the given camera then there relative rotation and translation from the IMU to Camera is returned.  Parameter ``cameraId``:     Camera Id of the camera which will be considered as destination. To which     Transformation matrix from the IMU will be found.  Parameter ``useSpecTranslation``:     Enabling this bool uses the translation information from the board design     data  Parameter ``unit``:     Units of the returned translation (default: centimeters)  Returns:     Returns a transformationMatrix which is 4x4 in homogeneous coordinate system  Matrix representation of transformation matrix \f[ \text{Transformation Matrix} = \left [ \begin{matrix} r_{00} & r_{01} & r_{02} & T_x \\ r_{10} & r_{11} & r_{12} & T_y \\ r_{20} & r_{21} & r_{22} & T_z \\ 0 & 0 & 0 & 1 \end{matrix} \right ] \f]
method
getLensPosition(self, cameraId: CameraBoardSocket) -> int: int
Get the lens position of the given camera  Parameter ``cameraId``:     of the camera with lens position is requested.  Returns:     lens position of the camera with given cameraId at which it was calibrated.
method
getSourceHeight(self, cameraId: CameraBoardSocket) -> int: int
Get the source height of the camera from the calibration data.  Parameter ``cameraId``:     Uses the cameraId to identify which camera source height to return  Returns:     the source height of the camera from the calibration data.
method
getSourceWidth(self, cameraId: CameraBoardSocket) -> int: int
Get the source width of the camera from the calibration data.  Parameter ``cameraId``:     Uses the cameraId to identify which camera source width to return  Returns:     the source width of the camera from the calibration data.
method
getStereoLeftCameraId(self) -> CameraBoardSocket: CameraBoardSocket
Get the camera id of the camera which is used as left camera of the stereo setup  Returns:     cameraID of the camera used as left camera
method
getStereoLeftRectificationRotation(self) -> list[list[float]]: list[list[float]]
Get the Stereo Left Rectification Rotation object  Returns:     returns a 3x3 rectification rotation matrix
method
getStereoRightCameraId(self) -> CameraBoardSocket: CameraBoardSocket
Get the camera id of the camera which is used as right camera of the stereo setup  Returns:     cameraID of the camera used as right camera
method
getStereoRightRectificationRotation(self) -> list[list[float]]: list[list[float]]
Get the Stereo Right Rectification Rotation object  Returns:     returns a 3x3 rectification rotation matrix
method
hasCalibrationData(self) -> bool: bool
Returns true when calibration payload is supported and contains camera calibration entries.  This check is not presence-only: it returns true only when `eepromData.version >= 4` (supported by intrinsics-dependent APIs) and `cameraData` is non-empty.
method
hasCameraCalibration(self, cameraId: CameraBoardSocket) -> bool: bool
Returns true when calibration is supported and contains data for a specific camera socket.  This is a presence-plus-version-compatibility check. It requires `hasCalibrationData()` to be true (currently `eepromData.version >= 4`) and a matching entry for `cameraId` in `cameraData`.
method
setAccelerometerCalibration(self, calibration: list[list[float]])
Set canonical accelerometer calibration [Q|b].  Parameter ``calibration``:     3x4 matrix in the form [[q00, q01, q02, b0], [q10, q11, q12, b1], [q20, q21,     q22, b2]]
method
method
setCameraExtrinsics(self, srcCameraId: CameraBoardSocket, destCameraId: CameraBoardSocket, rotationMatrix: list[list[float]], translation: list[float], specTranslation: list[float] = [0.0, 0.0, 0.0])
Set the Camera Extrinsics object  Translation values are stored in the default CalibrationHandler length unit: centimeters (cm).  Parameter ``srcCameraId``:     Camera Id of the camera which will be considered as relative origin.  Parameter ``destCameraId``:     Camera Id of the camera which will be considered as destination from     srcCameraId.  Parameter ``rotationMatrix``:     Rotation between srcCameraId and destCameraId origins.  Parameter ``translation``:     Translation between srcCameraId and destCameraId origins, in centimeters     (cm).  Parameter ``specTranslation``:     Translation between srcCameraId and destCameraId origins from the design, in     centimeters (cm).
method
method
setCameraType(self, cameraId: CameraBoardSocket, cameraModel: CameraModel)
Set the Camera Type object  Parameter ``cameraId``:     CameraId of the camera for which cameraModel Type is being updated.  Parameter ``cameraModel``:     Type of the model the camera represents
method
setDeviceName(self, deviceName: str)
Set the deviceName which responses to getDeviceName of Device  Parameter ``deviceName``:     Sets device name.
method
setDistortionCoefficients(self, cameraId: CameraBoardSocket, distortionCoefficients: list[float])
Sets the distortion Coefficients obtained from camera calibration  Parameter ``cameraId``:     Camera Id of the camera for which distortion coefficients are computed  Parameter ``distortionCoefficients``:     Distortion Coefficients of the respective Camera.
method
setFov(self, cameraId: CameraBoardSocket, hfov: float)
Set the Fov of the Camera  Parameter ``cameraId``:     Camera Id of the camera  Parameter ``hfov``:     Horizontal fov of the camera from Camera Datasheet
method
setGyroscopeCalibration(self, calibration: list[list[float]])
Set canonical gyroscope calibration [Q|b].  Parameter ``calibration``:     3x4 matrix in the form [[q00, q01, q02, b0], [q10, q11, q12, b1], [q20, q21,     q22, b2]]
method
setImuExtrinsics(self, destCameraId: CameraBoardSocket, rotationMatrix: list[list[float]], translation: list[float], specTranslation: list[float] = [0.0, 0.0, 0.0])
Set the Imu to Camera Extrinsics object  Translation values are stored in the default CalibrationHandler length unit: centimeters (cm).  Parameter ``destCameraId``:     Camera Id of the camera which will be considered as destination from IMU.  Parameter ``rotationMatrix``:     Rotation between srcCameraId and destCameraId origins.  Parameter ``translation``:     Translation between IMU and destCameraId origins, in centimeters (cm).  Parameter ``specTranslation``:     Translation between IMU and destCameraId origins from the design, in     centimeters (cm).
method
setImuParameters(self, imuParameters: ImuCalibrationParams)
Set full IMU parameter payload.  Parameter ``params``:     noise + accelerometer + gyroscope calibration parameters
method
setLensPosition(self, cameraId: CameraBoardSocket, lensPosition: int)
Sets the distortion Coefficients obtained from camera calibration  Parameter ``cameraId``:     Camera Id of the camera  Parameter ``lensPosition``:     lens posiotion value of the camera at the time of calibration
method
setProductName(self, productName: str)
Set the productName which acts as alisas for users to identify the device  Parameter ``productName``:     Sets product name (alias).
method
setStereoLeft(self, cameraId: CameraBoardSocket, rectifiedRotation: list[list[float]])
Set the Stereo Left Rectification object  Parameter ``cameraId``:     CameraId of the camera which will be used as left Camera of stereo Setup  Parameter ``rectifiedRotation``:     Rectification rotation of the left camera required for feature matching  Homography of the Left Rectification = Intrinsics_right * rectifiedRotation * inv(Intrinsics_left)
method
setStereoRight(self, cameraId: CameraBoardSocket, rectifiedRotation: list[list[float]])
Set the Stereo Right Rectification object  Parameter ``cameraId``:     CameraId of the camera which will be used as left Camera of stereo Setup  Parameter ``rectifiedRotation``:     Rectification rotation of the left camera required for feature matching  Homography of the Right Rectification = Intrinsics_right * rectifiedRotation * inv(Intrinsics_right)
method
validateCalibrationHandler(self, throwOnError: bool = True)
Validate Calibration handler properties and how they are set, so there is no: - Cycling links - Missing links - Dangling connections  Parameter ``throwOnError``:     Throw runtime error on failture.
class

depthai.CBACalibrationHandler

static method
method
method
eepromToJson(self) -> json: json
Get JSON representation of calibration data  Returns:     JSON structure
method
eepromToJsonFile(self, destPath: os.PathLike) -> bool: bool
Write raw calibration/board data to json file.  Parameter ``destPath``:     Full path to the json file in which raw calibration data will be stored  Returns:     True on success, false otherwise
method
method
method
method
method
getEepromData(self) -> EepromData: EepromData
Get the Eeprom Data object  Returns:     EepromData object which contains the raw calibration data
method
method
method
method
method
hasCalibrationData(self) -> bool: bool
Returns true when calibration payload is supported and contains camera calibration entries.  This check is not presence-only: it returns true only when `eepromData.version >= 4` (supported by intrinsics-dependent APIs) and `cameraData` is non-empty.
method
method
method
method
method
method
method
validateCalibrationHandler(self, throwOnError: bool = True)
Validate Calibration handler properties and how they are set, so there is no: - Cycling links - Missing links - Dangling connections  Parameter ``throwOnError``:     Throw runtime error on failture.
class

depthai.NNModelDescription

static method
NNModelDescription.fromYamlFile(yamlPath: os.PathLike, modelsPath: os.PathLike = '') -> NNModelDescription: NNModelDescription
Initialize NNModelDescription from yaml file If modelName is a relative path (e.g. ./yolo.yaml), it is used as is. If modelName is a full path (e.g. /home/user/models/yolo.yaml), it is used as is. If modelName is a model name (e.g. yolo) or a model yaml file (e.g. yolo.yaml), the function will use modelsPath if provided or the DEPTHAI_ZOO_MODELS_PATH environment variable and use a path made by combining the modelsPath and the model name to the yaml file. For instance, yolo -> ./depthai_models/yolo.yaml (if modelsPath or DEPTHAI_ZOO_MODELS_PATH are ./depthai_models)  Parameter ``modelName:``:     model name or yaml file path (string is implicitly converted to Path)  Parameter ``modelsPath:``:     Path to the models folder, use environment variable DEPTHAI_ZOO_MODELS_PATH     if not provided  Returns:     NNModelDescription
method
method
__str__(self) -> str: str
Convert NNModelDescription to string for printing purposes. This can be used for debugging.  Returns:     std::string: String representation
method
check(self) -> bool: bool
Check if the model description is valid (contains all required fields)  Returns:     bool: True if the model description is valid, false otherwise
method
saveToYamlFile(self, yamlPath: os.PathLike)
Save NNModelDescription to yaml file  Parameter ``yamlPath:``:     Path to yaml file
method
toString(self) -> str: str
Convert NNModelDescription to string for printing purposes. This can be used for debugging.  Returns:     std::string: String representation
property
compressionLevel
Compression level = OPTIONAL parameter
method
property
model
Model slug = REQUIRED parameter
method
property
modelPrecisionType
modelPrecisionType = OPTIONAL parameter
method
property
optimizationLevel
Optimization level = OPTIONAL parameter
method
property
platform
Hardware platform - RVC2, RVC3, RVC4, ... = REQUIRED parameter
method
property
snpeVersion
SNPE version = OPTIONAL parameter
method
class

depthai.RemoteConnection

method
__init__(self, address: str = '0.0.0.0', webSocketPort: int = 8765, serveFrontend: bool = True, httpPort: int = 8082)
Constructs a RemoteConnection instance.  Parameter ``address``:     The address to bind the connection to.  Parameter ``webSocketPort``:     The port for WebSocket communication.  Parameter ``serveFrontend``:     Whether to serve a frontend UI.  Parameter ``httpPort``:     The port for HTTP communication.
method
method
registerBinaryService(self, serviceName: str, callback: typing.Any)
Registers a binary service with a callback function.  Parameter ``serviceName``:     The name of the service.  Parameter ``callback``:     The callback function to handle requests.
method
registerPipeline(self, pipeline: Pipeline)
Registers a pipeline with the remote connection.  Parameter ``pipeline``:     The pipeline to register.
method
registerService(self, serviceName: str, callback: typing.Callable[[json], json])
Registers a service with a callback function.  Parameter ``serviceName``:     The name of the service.  Parameter ``callback``:     The callback function to handle requests.
method
removeTopic(self, topicName: str) -> bool: bool
Removes a topic from the remote connection.  Parameter ``topicName``:     The name of the topic to remove. @note After removing a topic any messages     sent to it will cause an exception to be called on the sender, since this     closes the queue.  Returns:     True if the topic was successfully removed, false otherwise.
method
waitKey(self, delay: int) -> int: int
Waits for a key event.  Parameter ``delayMs``:     The delay in milliseconds to wait for a key press.  Returns:     The key code of the pressed key.
class

depthai.SendSnapCallbackResult

method
property
property
property
property
property
property
class

depthai.EventsManager

method
method
sendEvent(self, name: str, tags: list[str] = [], extras: dict[str, str] = {}, associateFiles: list[str] = []) -> str|None: str|None
Send an event to the events service  Parameter ``name``:     Name of the event  Parameter ``tags``:     List of tags to send  Parameter ``extras``:     Extra data to send  Parameter ``associateFiles``:     List of associate files with ids  Returns:     LocalID of the sent Event
method
method
setCacheDir(self, cacheDir: str)
Set the cache directory for storing cached data. By default, the cache directory is set to /internal/private  Parameter ``cacheDir``:     Cache directory  Returns:     void
method
setCacheIfCannotSend(self, cacheIfCannotUpload: bool)
Set whether to cache data if it cannot be sent. By default, cacheIfCannotSend is set to false  Parameter ``cacheIfCannotSend``:     bool  Returns:     void
method
setLogResponse(self, logResponse: bool)
Set whether to log the responses from the server. By default, logResponse is set to false  Parameter ``logResponse``:     bool  Returns:     void
method
setVerifySsl(self, verifySsl: bool)
Set whether to verify the SSL certificate. By default, verifySsl is set to false  Parameter ``verifySsl``:     bool  Returns:     void
method
waitForPendingUploads(self, timeoutMs: int = 0) -> bool: bool
Wait for pending snaps/events to be processed by the background upload thread  Parameter ``timeoutMs``:     Timeout in milliseconds. 0 means wait until uploads are finished, connection     is dropped, or manager is stopped  Returns:     true if the pending data was uploaded before timeout, false if not - either     because of timeout, dropped connection, or shutdown