intel/scenescape-camcalibration

Intel® SceneScape's Camera Calibration Service

Auto camera calibration service computes camera parameters automatically instead of complicated manual calibration methods.

Overview

The calibration process begins with the client sending a heartbeat command to verify if the calibration service is active. Upon receiving this, the service responds with its current status, such as "running" or "alive." If the status confirms that the service is running, the client issues a command to initiate camera localization. The calibration service then processes this request and returns the resulting camera pose data.

The auto calibration services supports two types of camera calibration methods:

• AprilTag Calibration: This method uses fiducial markers called AprilTags placed within the scene. By detecting these markers in the camera's view, the service calculates the camera's position, enhancing calibration accuracy and efficiency.

• Markerless Calibration: This approach leverages raw RGBD data from a Polycam scan to estimate the camera's pose in the scene, eliminating the need for physical markers.

Documentation

• Overview

  • https://github.com/open-edge-platform/scenescape/blob/release-2025.2/autocalibration/docs/user-guide/overview.md: A high-level introduction.

• Getting Started

  • https://github.com/open-edge-platform/scenescape/blob/release-2025.2/autocalibration/docs/user-guide/get-started.md: Step-by-step guide to getting started with the microservce.

• Deployment

  • https://github.com/open-edge-platform/scenescape/blob/release-2025.2/autocalibration/docs/user-guide/How-to-build-source.md: Step-by-step guide to building from source.

• API Reference

  • https://github.com/open-edge-platform/scenescape/blob/release-2025.2/autocalibration/docs/user-guide/api-docs/autocalibration-api.yaml: Comprehensive reference for the request/response communication endpoints.

Community

To report a bug, file a documentation issue, or submit a feature request, please open a https://github.com/open-edge-platform/scenescape/issues.

Contributing

We welcome contributions! Check out our https://github.com/open-edge-platform/scenescape/blob/main/CONTRIBUTING.md to get started.

Supported versions

• v2025.2
• v1.4.0

License

Intel® SceneScape repository is licensed under APACHE 2.0 LICENSE.

Disclaimers

This container image is intended for demo purposes only and not intended for production use. To receive expanded security maintenance from Canonical on the Ubuntu base layer, you may follow the how-to guide to enable Ubuntu Pro in a Dockerfile which will require the image to be rebuilt.

Depending on your deployment, Intel® SceneScape may utilize FFmpeg and/or GStreamer.

FFmpeg is an open source project licensed under LGPL and GPL. See FFmpeg License and Legal ***ations. You are solely responsible for determining if your use of FFmpeg requires any additional licenses. Intel is not responsible for obtaining any such licenses, nor liable for any licensing fees due, in connection with your use of FFmpeg.

GStreamer is an open source framework licensed under LGPL. See Licensing your applications and plugins for use with GStreamer. You are solely responsible for determining if your use of GStreamer requires any additional licenses. Intel is not responsible for obtaining any such licenses, nor liable for any licensing fees due, in connection with your use of GStreamer.