mkr's profile - activity

I am also really interested in Python 3 support. Are there any 'official' plans to update OpenCV to Python 3? If not, would anyone be interested in starting such a project? Maybe it won't be that much harder than just using the 2to3 script :)

In short: Homography relates two views of a set of coplanar points. The essential (E) and the fundamental (F) matrix relate two views of a set of points that don't need to be coplanar. The difference between E and F is that E only works for pairs of points whose image coordinates have been normalized beforehand - their raw image coordinates have been transformed by the camera matrices you get when you perform camera calibration.

For a stereo pair, the intrinsic parameters are the ones related to the cameras themselves, that is their respective distortion coefficients and calibration matrices. The extrinsic parameters are the relative rotation and translation between the cameras.

If you could tell me a bit more about what you'd like to - what is your input data and what projection matrix you'd like to compute - I might be able to help a little more.

Quickly running through your program - the debugger shows, that the size of good_matches and hence also the obj and scene is zero. Originally, 9 matches are found, but they are discarded when you apply the max_dist and min_dist constraints. I strongly recommend you to make friends with the debugger :) Good luck with fixing the code!