I want to get more a more accurate point cloud and uv-mapping for the Softkinetic Depthsense by calibrating the intrinsic and extrinsic parameters of the depthsense using the ROS camera_calibration package.
The output matrices of the camera_calibration package are:
- Distortion parameters (D)
- Intrinsic camera matrix (K)
- Rectification matrix (R)
- Projection matrix of the processed (rectified) image (P)
The Depthsense SDK has the option to set the camera parameters in the StereoCameraParameters struct.
How do I get the camera pose (extrinsic parameters) from the camera_calibration output (D, K, R and P)?
The projection matrix (P) contains is the projection onto the rectified image. Decomposing this matrix into a translation and rotation would give the extrinsic parameters of the virtual, rectified camera. What I need to set in the Depthsense SDK are the real camera extrinsics.
Originally posted by Ronald on ROS Answers with karma: 103 on 2015-03-06
Post score: 1
Original comments
Comment by Introcert on 2017-08-07:
Hi , I wonder if you have solved this question. I also have the question about how to get the camera extrinsics . And I am desired to get your help. Thanks a lot!