triangulatePoints arguments
nicolasrosa opened this issue · 0 comments
nicolasrosa commented
Hello @gaoxiang12,
According to the official documentation of OpenCV, the arguments of cv2::triangulatePoints()
should be the projection matrices and the feature points coordinates, but I think it is not clear if it should be in pixel or in camera coordinates. In the book, you use only the extrinsic transformations (T1w and T21) as inputs and the normalized coordinates, is this correct?
https://docs.opencv.org/3.4.17/d9/d0c/group__calib3d.html#gadb7d2dfcc184c1d2f496d8639f4371c0
In this link, we can see that this is not a consensus.
https://www.programcreek.com/python/example/110665/cv2.triangulatePoints