# 深度后处理 本示例展示了如何在设备本身上运行深度后处理滤波器，以减少噪点、平滑深度图并整体提升深度图质量。后处理可以添加到 [StereoDepth](https://docs.luxonis.com/software/depthai-components/nodes/stereo_depth.md) 节点中。 ## Demo ## 深度滤波器 ### 中值滤波 这是一种非保边中值滤波器，可用于减少噪声并平滑深度图。中值滤波器由硬件实现，因此是最快的滤波器。 ### depthai.StereoDepthConfig.MedianFilter Kind: Class Median filter config Members: MEDIAN_OFF KERNEL_3x3 KERNEL_5x5 KERNEL_7x7 #### KERNEL_3x3: typing.ClassVar[MedianFilter] Kind: Class Variable #### KERNEL_5x5: typing.ClassVar[MedianFilter] Kind: Class Variable #### KERNEL_7x7: typing.ClassVar[MedianFilter] Kind: Class Variable #### MEDIAN_OFF: typing.ClassVar[MedianFilter] Kind: Class Variable #### __members__: typing.ClassVar[dict[str, MedianFilter]] Kind: Class Variable #### __eq__(self, other: typing.Any) -> bool: bool Kind: Method #### __getstate__(self) -> int: int Kind: Method #### __hash__(self) -> int: int Kind: Method #### __index__(self) -> int: int Kind: Method #### __init__(self, value: typing.SupportsInt) Kind: Method #### __int__(self) -> int: int Kind: Method #### __ne__(self, other: typing.Any) -> bool: bool Kind: Method #### __repr__(self) -> str: str Kind: Method #### __setstate__(self, state: typing.SupportsInt) Kind: Method #### __str__(self) -> str: str Kind: Method #### name Kind: Property #### value Kind: Property ### 散斑滤波 散斑滤波器用于减少散斑噪声。散斑噪声是指相邻视差/深度像素之间存在巨大差异的区域，散斑滤波器尝试滤除这类区域。 ### depthai.StereoDepthConfig.PostProcessing.SpeckleFilter Kind: Class Speckle filtering. Removes speckle noise. #### __init__(self: RawStereoDepthConfig.PostProcessing.SpeckleFilter) Kind: Method #### differenceThreshold Kind: Property Maximum difference between neighbor disparity pixels to put them into the same blob. Units in disparity integer levels. #### differenceThreshold.setter(self, arg0: typing.SupportsInt) Kind: Method #### enable Kind: Property Whether to enable or disable the filter. #### enable.setter(self, arg0: bool) Kind: Method #### speckleRange Kind: Property Speckle search range. #### speckleRange.setter(self, arg0: typing.SupportsInt) Kind: Method ### 时域滤波 时域滤波器旨在通过基于先前帧操作每个像素值来提升深度数据的持久性。该滤波器对数据执行单次遍历，在调整深度值的同时更新跟踪历史。当像素数据缺失或无效时，滤波器使用用户定义的持久性模式来决定是否用存储的数据来修正缺失值。需要注意的是，由于依赖历史数据，该滤波器可能会引入明显的模糊/拖影伪影，因此最适合静态场景。 ### depthai.StereoDepthConfig.PostProcessing.TemporalFilter Kind: Class Temporal filtering with optional persistence. #### depthai.StereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode Kind: Class 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 : ##### PERSISTENCY_INDEFINITELY: typing.ClassVar[RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode] Kind: Class Variable ##### PERSISTENCY_OFF: typing.ClassVar[RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode] Kind: Class Variable ##### VALID_1_IN_LAST_2: typing.ClassVar[RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode] Kind: Class Variable ##### VALID_1_IN_LAST_5: typing.ClassVar[RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode] Kind: Class Variable ##### VALID_1_IN_LAST_8: typing.ClassVar[RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode] Kind: Class Variable ##### VALID_2_IN_LAST_3: typing.ClassVar[RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode] Kind: Class Variable ##### VALID_2_IN_LAST_4: typing.ClassVar[RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode] Kind: Class Variable ##### VALID_2_OUT_OF_8: typing.ClassVar[RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode] Kind: Class Variable ##### VALID_8_OUT_OF_8: typing.ClassVar[RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode] Kind: Class Variable ##### __members__: typing.ClassVar[dict[str, RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode]] Kind: Class Variable ##### __eq__(self, other: typing.Any) -> bool: bool Kind: Method ##### __getstate__(self) -> int: int Kind: Method ##### __hash__(self) -> int: int Kind: Method ##### __index__(self: RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode) -> int: int Kind: Method ##### __init__(self: RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode, value: typing.SupportsInt) Kind: Method ##### __int__(self: RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode) -> int: int Kind: Method ##### __ne__(self, other: typing.Any) -> bool: bool Kind: Method ##### __repr__(self) -> str: str Kind: Method ##### __setstate__(self: RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode, state: typing.SupportsInt) Kind: Method ##### __str__(self) -> str: str Kind: Method ##### name Kind: Property ##### value Kind: Property #### __init__(self: RawStereoDepthConfig.PostProcessing.TemporalFilter) Kind: Method #### alpha Kind: Property 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. #### alpha.setter(self, arg0: typing.SupportsFloat) Kind: Method #### delta Kind: Property 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. #### delta.setter(self, arg0: typing.SupportsInt) Kind: Method #### enable Kind: Property Whether to enable or disable the filter. #### enable.setter(self, arg0: bool) Kind: Method #### persistencyMode Kind: Property Persistency mode. If the current disparity/depth value is invalid, it will be replaced by an older value, based on persistency mode. #### persistencyMode.setter(self, arg0: RawStereoDepthConfig.PostProcessing.TemporalFilter.PersistencyMode) Kind: Method ### 空间滤波 空间保边滤波器会用有效的邻近深度像素填充无效的深度像素。它执行一系列一维水平和垂直遍历（迭代），以增强重建数据的平滑度。该滤波器基于[这篇研究论文](https://www.inf.ufrgs.br/~eslgastal/DomainTransform/)。 ### depthai.StereoDepthConfig.PostProcessing.SpatialFilter Kind: Class 1D edge-preserving spatial filter using high-order domain transform. #### __init__(self: RawStereoDepthConfig.PostProcessing.SpatialFilter) Kind: Method #### alpha Kind: Property The Alpha factor in an exponential moving average with Alpha=1 - no filter. Alpha = 0 - infinite filter. Determines the amount of smoothing. #### alpha.setter(self, arg0: typing.SupportsFloat) Kind: Method #### delta Kind: Property 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. #### delta.setter(self, arg0: typing.SupportsInt) Kind: Method #### enable Kind: Property Whether to enable or disable the filter. #### enable.setter(self, arg0: bool) Kind: Method #### holeFillingRadius Kind: Property 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. #### holeFillingRadius.setter(self, arg0: typing.SupportsInt) Kind: Method #### numIterations Kind: Property Number of iterations over the image in both horizontal and vertical direction. #### numIterations.setter(self, arg0: typing.SupportsInt) Kind: Method ### 阈值滤波 阈值滤波器会滤除所有超出配置的最小/最大阈值范围的视差/深度像素。 ```python class ThresholdFilter: ''' 空间保边滤波器会用有效的邻近深度像素填充无效的深度像素。 它执行一系列一维水平和垂直遍历（迭代），以增强重建数据的平滑度。 该滤波器基于[这篇研究论文](https://www.inf.ufrgs.br/~eslgastal/DomainTransform/)。 ''' ``` ### 相似示例： * [深度预览](https://docs.luxonis.com/software/depthai/examples/depth_preview.md) * [主机立体深度](https://docs.luxonis.com/software/depthai/examples/stereo_depth_from_host.md) ## 设置 请运行[安装脚本](https://github.com/luxonis/depthai-python/blob/main/examples/install_requirements.py)以下载所有必需的依赖项。请注意，此脚本必须在 git 上下文中运行，因此您需要先下载 [depthai-python](https://github.com/luxonis/depthai-python) 仓库，然后运行该脚本。 ```bash git clone https://github.com/luxonis/depthai-python.git cd depthai-python/examples python3 install_requirements.py ``` 更多信息，请参考[安装指南](https://docs.luxonis.com/software/depthai/manual-install.md)。 ## 源代码 #### Python ```python #!/usr/bin/env python3 import cv2 import depthai as dai import numpy as np # Closer-in minimum depth, disparity range is doubled (from 95 to 190): extended_disparity = False # Better accuracy for longer distance, fractional disparity 32-levels: subpixel = False # Better handling for occlusions: lr_check = True # Create pipeline pipeline = dai.Pipeline() # Define sources and outputs monoLeft = pipeline.create(dai.node.MonoCamera) monoRight = pipeline.create(dai.node.MonoCamera) depth = pipeline.create(dai.node.StereoDepth) xout = pipeline.create(dai.node.XLinkOut) xout.setStreamName("disparity") # Properties monoLeft.setResolution(dai.MonoCameraProperties.SensorResolution.THE_400_P) monoLeft.setCamera("left") monoRight.setResolution(dai.MonoCameraProperties.SensorResolution.THE_400_P) monoRight.setCamera("right") # Create a node that will produce the depth map (using disparity output as it's easier to visualize depth this way) depth.setDefaultProfilePreset(dai.node.StereoDepth.PresetMode.HIGH_DENSITY) # Options: MEDIAN_OFF, KERNEL_3x3, KERNEL_5x5, KERNEL_7x7 (default) depth.initialConfig.setMedianFilter(dai.MedianFilter.KERNEL_7x7) depth.setLeftRightCheck(lr_check) depth.setExtendedDisparity(extended_disparity) depth.setSubpixel(subpixel) config = depth.initialConfig.get() config.postProcessing.speckleFilter.enable = False config.postProcessing.speckleFilter.speckleRange = 50 config.postProcessing.temporalFilter.enable = True config.postProcessing.spatialFilter.enable = True config.postProcessing.spatialFilter.holeFillingRadius = 2 config.postProcessing.spatialFilter.numIterations = 1 config.postProcessing.thresholdFilter.minRange = 400 config.postProcessing.thresholdFilter.maxRange = 15000 config.postProcessing.decimationFilter.decimationFactor = 1 depth.initialConfig.set(config) # Linking monoLeft.out.link(depth.left) monoRight.out.link(depth.right) depth.disparity.link(xout.input) # Connect to device and start pipeline with dai.Device(pipeline) as device: # Output queue will be used to get the disparity frames from the outputs defined above q = device.getOutputQueue(name="disparity", maxSize=4, blocking=False) while True: inDisparity = q.get() # blocking call, will wait until a new data has arrived frame = inDisparity.getFrame() # Normalization for better visualization frame = (frame * (255 / depth.initialConfig.getMaxDisparity())).astype(np.uint8) cv2.imshow("disparity", frame) # Available color maps: https://docs.opencv.org/3.4/d3/d50/group__imgproc__colormap.html frame = cv2.applyColorMap(frame, cv2.COLORMAP_JET) cv2.imshow("disparity_color", frame) if cv2.waitKey(1) == ord('q'): break ``` #### C++ ```cpp #include // Inludes common necessary includes for development using depthai library #include "depthai/depthai.hpp" // Closer-in minimum depth, disparity range is doubled (from 95 to 190): static std::atomic extended_disparity{false}; // Better accuracy for longer distance, fractional disparity 32-levels: static std::atomic subpixel{false}; // Better handling for occlusions: static std::atomic lr_check{true}; int main() { // Create pipeline dai::Pipeline pipeline; // Define sources and outputs auto monoLeft = pipeline.create(); auto monoRight = pipeline.create(); auto depth = pipeline.create(); auto xout = pipeline.create(); xout->setStreamName("disparity"); // Properties monoLeft->setResolution(dai::MonoCameraProperties::SensorResolution::THE_400_P); monoLeft->setCamera("left"); monoRight->setResolution(dai::MonoCameraProperties::SensorResolution::THE_400_P); monoRight->setCamera("right"); // Create a node that will produce the depth map (using disparity output as it's easier to visualize depth this way) depth->setDefaultProfilePreset(dai::node::StereoDepth::PresetMode::HIGH_DENSITY); // Options: MEDIAN_OFF, KERNEL_3x3, KERNEL_5x5, KERNEL_7x7 (default) depth->initialConfig.setMedianFilter(dai::MedianFilter::KERNEL_7x7); depth->setLeftRightCheck(lr_check); depth->setExtendedDisparity(extended_disparity); depth->setSubpixel(subpixel); auto config = depth->initialConfig.get(); config.postProcessing.speckleFilter.enable = false; config.postProcessing.speckleFilter.speckleRange = 50; config.postProcessing.temporalFilter.enable = true; config.postProcessing.spatialFilter.enable = true; config.postProcessing.spatialFilter.holeFillingRadius = 2; config.postProcessing.spatialFilter.numIterations = 1; config.postProcessing.thresholdFilter.minRange = 400; config.postProcessing.thresholdFilter.maxRange = 15000; config.postProcessing.decimationFilter.decimationFactor = 1; depth->initialConfig.set(config); // Linking monoLeft->out.link(depth->left); monoRight->out.link(depth->right); depth->disparity.link(xout->input); // Connect to device and start pipeline dai::Device device(pipeline); // Output queue will be used to get the disparity frames from the outputs defined above auto q = device.getOutputQueue("disparity", 4, false); while(true) { auto inDepth = q->get(); auto frame = inDepth->getFrame(); // Normalization for better visualization frame.convertTo(frame, CV_8UC1, 255 / depth->initialConfig.getMaxDisparity()); cv::imshow("disparity", frame); // Available color maps: https://docs.opencv.org/3.4/d3/d50/group__imgproc__colormap.html cv::applyColorMap(frame, frame, cv::COLORMAP_JET); cv::imshow("disparity_color", frame); int key = cv::waitKey(1); if(key == 'q' || key == 'Q') { return 0; } } return 0; } ``` ## 流水线 ### examples/depth_post_processing.pipeline.json ```json {"pipeline":{"connections":[{"node1Id":0,"node1Output":"out","node1OutputGroup":"","node2Id":2,"node2Input":"left","node2InputGroup":""},{"node1Id":1,"node1Output":"out","node1OutputGroup":"","node2Id":2,"node2Input":"right","node2InputGroup":""},{"node1Id":2,"node1Output":"disparity","node1OutputGroup":"","node2Id":3,"node2Input":"in","node2InputGroup":""}],"globalProperties":{"calibData":null,"cameraTuningBlobSize":null,"cameraTuningBlobUri":"","leonCssFrequencyHz":700000000,"leonMssFrequencyHz":700000000,"pipelineName":null,"pipelineVersion":null,"sippBufferSize":18432,"sippDmaBufferSize":16384,"xlinkChunkSize":-1},"nodes":[[0,{"id":0,"ioInfo":[[["","inputControl"],{"blocking":true,"group":"","id":1,"name":"inputControl","queueSize":8,"type":3,"waitForMessage":false}],[["","out"],{"blocking":false,"group":"","id":2,"name":"out","queueSize":8,"type":0,"waitForMessage":false}],[["","raw"],{"blocking":false,"group":"","id":3,"name":"raw","queueSize":8,"type":0,"waitForMessage":false}],[["","frameEvent"],{"blocking":false,"group":"","id":4,"name":"frameEvent","queueSize":8,"type":0,"waitForMessage":false}]],"name":"MonoCamera","properties":{"boardSocket":-1,"cameraName":"left","fps":30,"imageOrientation":-1,"initialControl":{"aeLockMode":false,"aeMaxExposureTimeUs":0,"aeRegion":{"height":0,"priority":0,"width":0,"x":0,"y":0},"afRegion":{"height":0,"priority":0,"width":0,"x":0,"y":0},"antiBandingMode":0,"autoFocusMode":3,"awbLockMode":false,"awbMode":0,"brightness":0,"captureIntent":0,"chromaDenoise":0,"cmdMask":0,"contrast":0,"controlMode":0,"effectMode":0,"expCompensation":0,"expManual":{"exposureTimeUs":0,"frameDurationUs":0,"sensitivityIso":0},"frameSyncMode":0,"lensPosAutoInfinity":0,"lensPosAutoMacro":0,"lensPosition":0,"lensPositionRaw":0,"lowPowerNumFramesBurst":0,"lowPowerNumFramesDiscard":0,"lumaDenoise":0,"saturation":0,"sceneMode":0,"sharpness":0,"strobeConfig":{"activeLevel":0,"enable":0,"gpioNumber":0},"strobeTimings":{"durationUs":0,"exposureBeginOffsetUs":0,"exposureEndOffsetUs":0},"wbColorTemp":0},"isp3aFps":0,"numFramesPool":3,"numFramesPoolRaw":3,"rawPacked":null,"resolution":2}}],[1,{"id":1,"ioInfo":[[["","inputControl"],{"blocking":true,"group":"","id":5,"name":"inputControl","queueSize":8,"type":3,"waitForMessage":false}],[["","out"],{"blocking":false,"group":"","id":6,"name":"out","queueSize":8,"type":0,"waitForMessage":false}],[["","raw"],{"blocking":false,"group":"","id":7,"name":"raw","queueSize":8,"type":0,"waitForMessage":false}],[["","frameEvent"],{"blocking":false,"group":"","id":8,"name":"frameEvent","queueSize":8,"type":0,"waitForMessage":false}]],"name":"MonoCamera","properties":{"boardSocket":-1,"cameraName":"right","fps":30,"imageOrientation":-1,"initialControl":{"aeLockMode":false,"aeMaxExposureTimeUs":0,"aeRegion":{"height":0,"priority":0,"width":0,"x":0,"y":0},"afRegion":{"height":0,"priority":0,"width":0,"x":0,"y":0},"antiBandingMode":0,"autoFocusMode":3,"awbLockMode":false,"awbMode":0,"brightness":0,"captureIntent":0,"chromaDenoise":0,"cmdMask":0,"contrast":0,"controlMode":0,"effectMode":0,"expCompensation":0,"expManual":{"exposureTimeUs":0,"frameDurationUs":0,"sensitivityIso":0},"frameSyncMode":0,"lensPosAutoInfinity":0,"lensPosAutoMacro":0,"lensPosition":0,"lensPositionRaw":0,"lowPowerNumFramesBurst":0,"lowPowerNumFramesDiscard":0,"lumaDenoise":0,"saturation":0,"sceneMode":0,"sharpness":0,"strobeConfig":{"activeLevel":0,"enable":0,"gpioNumber":0},"strobeTimings":{"durationUs":0,"exposureBeginOffsetUs":0,"exposureEndOffsetUs":0},"wbColorTemp":0},"isp3aFps":0,"numFramesPool":3,"numFramesPoolRaw":3,"rawPacked":null,"resolution":2}}],[2,{"id":2,"ioInfo":[[["","inputConfig"],{"blocking":false,"group":"","id":9,"name":"inputConfig","queueSize":4,"type":3,"waitForMessage":false}],[["","left"],{"blocking":false,"group":"","id":10,"name":"left","queueSize":8,"type":3,"waitForMessage":true}],[["","debugExtDispLrCheckIt1"],{"blocking":false,"group":"","id":22,"name":"debugExtDispLrCheckIt1","queueSize":8,"type":0,"waitForMessage":false}],[["","right"],{"blocking":false,"group":"","id":11,"name":"right","queueSize":8,"type":3,"waitForMessage":true}],[["","syncedLeft"],{"blocking":false,"group":"","id":12,"name":"syncedLeft","queueSize":8,"type":0,"waitForMessage":false}],[["","depth"],{"blocking":false,"group":"","id":13,"name":"depth","queueSize":8,"type":0,"waitForMessage":false}],[["","disparity"],{"blocking":false,"group":"","id":14,"name":"disparity","queueSize":8,"type":0,"waitForMessage":false}],[["","syncedRight"],{"blocking":false,"group":"","id":15,"name":"syncedRight","queueSize":8,"type":0,"waitForMessage":false}],[["","debugDispCostDump"],{"blocking":false,"group":"","id":20,"name":"debugDispCostDump","queueSize":8,"type":0,"waitForMessage":false}],[["","debugDispLrCheckIt2"],{"blocking":false,"group":"","id":21,"name":"debugDispLrCheckIt2","queueSize":8,"type":0,"waitForMessage":false}],[["","rectifiedLeft"],{"blocking":false,"group":"","id":16,"name":"rectifiedLeft","queueSize":8,"type":0,"waitForMessage":false}],[["","debugExtDispLrCheckIt2"],{"blocking":false,"group":"","id":23,"name":"debugExtDispLrCheckIt2","queueSize":8,"type":0,"waitForMessage":false}],[["","rectifiedRight"],{"blocking":false,"group":"","id":17,"name":"rectifiedRight","queueSize":8,"type":0,"waitForMessage":false}],[["","confidenceMap"],{"blocking":false,"group":"","id":24,"name":"confidenceMap","queueSize":8,"type":0,"waitForMessage":false}],[["","outConfig"],{"blocking":false,"group":"","id":18,"name":"outConfig","queueSize":8,"type":0,"waitForMessage":false}],[["","debugDispLrCheckIt1"],{"blocking":false,"group":"","id":19,"name":"debugDispLrCheckIt1","queueSize":8,"type":0,"waitForMessage":false}]],"name":"StereoDepth","properties":{"alphaScaling":null,"baseline":null,"depthAlignCamera":-1,"depthAlignmentUseSpecTranslation":null,"disparityToDepthUseSpecTranslation":null,"enableRectification":true,"enableRuntimeStereoModeSwitch":false,"focalLength":null,"focalLengthFromCalibration":true,"height":null,"initialConfig":{"algorithmControl":{"centerAlignmentShiftFactor":null,"customDepthUnitMultiplier":1000,"depthAlign":0,"depthUnit":2,"disparityShift":0,"enableExtended":false,"enableLeftRightCheck":true,"enableSubpixel":false,"leftRightCheckThreshold":10,"numInvalidateEdgePixels":0,"subpixelFractionalBits":3},"censusTransform":{"enableMeanMode":true,"kernelMask":0,"kernelSize":-1,"threshold":0},"costAggregation":{"divisionFactor":1,"horizontalPenaltyCostP1":250,"horizontalPenaltyCostP2":500,"verticalPenaltyCostP1":250,"verticalPenaltyCostP2":500},"costMatching":{"confidenceThreshold":245,"disparityWidth":1,"enableCompanding":false,"invalidDisparityValue":0,"linearEquationParameters":{"alpha":0,"beta":2,"threshold":127}},"postProcessing":{"bilateralSigmaValue":0,"brightnessFilter":{"maxBrightness":256,"minBrightness":0},"decimationFilter":{"decimationFactor":1,"decimationMode":0},"median":7,"spatialFilter":{"alpha":0.5,"delta":0,"enable":true,"holeFillingRadius":2,"numIterations":1},"speckleFilter":{"enable":false,"speckleRange":50},"temporalFilter":{"alpha":0.4000000059604645,"delta":0,"enable":true,"persistencyMode":3},"thresholdFilter":{"maxRange":15000,"minRange":400}}},"mesh":{"meshLeftUri":"","meshRightUri":"","meshSize":null,"stepHeight":16,"stepWidth":16},"numFramesPool":3,"numPostProcessingMemorySlices":-1,"numPostProcessingShaves":-1,"outHeight":null,"outKeepAspectRatio":true,"outWidth":null,"rectificationUseSpecTranslation":null,"rectifyEdgeFillColor":0,"useHomographyRectification":null,"width":null}}],[3,{"id":3,"ioInfo":[[["","in"],{"blocking":true,"group":"","id":25,"name":"in","queueSize":8,"type":3,"waitForMessage":true}]],"name":"XLinkOut","properties":{"maxFpsLimit":-1,"metadataOnly":false,"streamName":"disparity"}}]]}} ``` ### 需要帮助？ 请前往 [OAKChina 官网](https://www.oakchina.cn/) 获取技术支持或解答您的任何疑问。