Robst's profile - activity

Thank you, it helped me a lot

Hello:

objectPoints are points expressed in the object coordinate space, for example, for a chess calibration pattern, we can fix a coordinate system in one of the corners of the plane so that the chess board is on the x-y plane an all chess corners have a z-coordinate value of zero. You would supply to the solvePnP function the coordinates of the chess corners expressed in this coordinate system. Notice that for this set of points we haven't used the camera coordinate system.

To transform your current objectPoints to the object coordinate system you have to find the transformation from the camera coordinate system to the object coordinate system. solvePnP will be handy for this. Also, take into account that if you obtain coordinate system C2 by translating coordinate system C1 by T and rotating it by a rotation matrix R , the inverse transformation is given by a rotation by R^t (the transpose) and a translation -RT.

Hope this helps.

Hello:

For an assignment in stereo matching I have to program some stereo confidence measures, like Left-Right consistency or Peak Ratio, and estimate the quality of the obtained disparity map for selected stereo matchers, like OpenCV's StereoBM and StereoSGBM.

For some of those confidence measures, the 3D Data Cost Matrix is required. This matrix stores, for each pixel p in the image and for each possible disparity value d, d_min <= d <= d_max, the cost to associate d to p. A matcher using the "Winner takes it all" strategy, would return as the selected disparity the value d* that is minimum.

I wonder if it is possible to get the 3D Data Cost Matrix from the StereoBM and StereoSGBM implementation. I've reviewed the code of StereoSGBM and there's a function called calcPixelCostBT that I think calculates this matrix, but I'm not totally sure.

I hope someone can shed some light into this issue.

Best regards!

Robst