How to obtain the real world coordinate from bounding box

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson )
• DeepStream Version(latest)
• TensorRT Version(latest)
• Issue Type( questions)
**• Requirement details

I would like to implement a deep stream pipeline which after having the bounding box, The real-world coordinate of the object shown on the output. I have the camera coordinate through GPS and I have the velocity of the camera. The camera is moving and the detected object is moving as well.

Regards

3

Seems you need to use 3D model detection, but current DS cannot support it.

4

Hi, Actually no I do not need the 3D model, I need to know the kind of 3D camera calibration with a moving object and camera + Depth

5

There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

OK, could you share more specific info with us, so we can help further.