此页面由 AI 自动翻译。查看英文原版
最后更新

本页目录

  • Automatic Calibration Procedures
  • Multi-sensor and FFC workflows
  • Scenery guidelines
  • Developer Integration
  • Clone & Run the Example
  • Implement into your projects

DynamicCalibration

最后更新
DynamicCalibration is a self-healing, on-device recalibration tool built into DepthAI 3.0. It allows stereo depth cameras to automatically monitor and restore their stereo extrinsic calibration, ensuring stable depth accuracy over time — even after thermal shifts, mechanical shocks, or mounting changes degrade factory alignment.The current multi-sensor work also extends this workflow to FFC and other multi-camera layouts, where calibration may need to stay consistent across more than one camera pair.

Key capabilities

  • Restore depth performance — bring your disparity map back to crisp, geometrically consistent output.
  • Continuous or manual operation — works in real time or via manual triggers.
  • Calibration health monitoring — check alignment drift without modifying the device.
  • Fast, robust recalibration — typically completes in seconds using live stereo input.
  • No special targets needed — runs in natural scenes with feature-rich visual content.
  • Supports all stereo cameras running DepthAI 3.0 — including OAK-D, OAK-D-Lite, OAK-D Pro, CM4 PoE, and more.
  • Extending to multi-sensor calibration — newer workflows can calibrate connected sensor graphs and expose socket-keyed diagnostics.

Try it out in OAK Viewer (no code required)

The fastest way to test the capabilities of DynamicCalibration is by using the latest version of the OAK-Viewer:

OAK Viewer

OAK Viewer is a desktop GUI application that allows you to visualize the camera's streams and interact with the device. It is available for Windows, macOS, and Linux.
Click here to get started
OAK Viewer

Automatic Calibration Procedures

AutoCalibration provides startup and continuous recalibration procedures under one feature.

ON_START and CONTINUOUS

  • Start DCL automatically with ON_START before normal operation.
  • Keep DCL running with CONTINUOUS for ongoing self-healing during runtime.
  • No manual DCL trigger needed in your application flow.
  • Better chance of stable calibration in both startup and long-running deployments.
See integration details

Multi-sensor and FFC workflows

DynamicCalibration is not limited to a single stereo pair. It also supports:
  • Multi-sensor calibration solved as one connected rig instead of unrelated pairwise updates.
  • Known-baseline recalibration, where camera centers stay fixed and only orientation drift is corrected.
  • Free-form recalibration for unknown baselines, useful on FFC setups that do not yet have reliable rig extrinsics.
  • Socket-keyed diagnostics so applications can reason about coverage and rotation deltas per connected camera.
For implementation details, command behavior, and code examples, continue to the technical DynamicCalibration page.

Scenery guidelines

良好的校准场景使算法更容易检测、匹配和跟踪特征。推荐的特性:
  • 包含多个深度的纹理对象。
  • 避免空白墙壁或无特征表面。
  • 缓慢移动相机以覆盖整个视场;避免突然移动。
建议原始图像与特征覆盖(绿色)
✅确保丰富的纹理和视觉细节 - 丰富的纹理、边缘和均匀分布在视场中的物体创造了理想的校准条件
🚫避免平坦或无特征的表面 - 缺乏纹理表面或视觉上独特的物体提供的可用特征很少
🚫避免反射和透明表面 - 反射和透明表面会产生错误的 3D 特征
🚫避免黑暗场景 - 低对比度、阴影和光线不足的场景产生的可检测特征很少
🚫避免重复图案 - 许多图案区域看起来太相似,难以区分

Developer Integration

Dynamic Calibration is included in DepthAI and does require extra installation. Run the following example to get an overview of the implementation.

Clone & Run the Example

Command Line
1git clone https://github.com/luxonis/depthai-core.git
2cd depthai-core/
3python3 -m venv venv
4source venv/bin/activate
5python3 examples/python/install_requirements.py
6python3 examples/python/DynamicCalibration/calibration_integration.py

Implement into your projects

Follow the dynamic calibration library documentation to learn how to implement Dynamic Calibration into your own projects.