Image matching using goodFeaturesToTrack

asked 2016-07-20 12:04:41 -0500

n.argirop gravatar image

I already tried to detect corners using goodFeaturesToTrack and then use those corners in BFMatcher, which doesn't accept them and asks for keypoints instead. Is it possible to make it work somehow? The reason why I don't use SIFT, SURF, etc. is because of the calculation speed and the fact that I can manipulate the dispersion of the points on the image, thus being able to use much fewer points to achieve a good dispersion on the whole image.

I am using opencv 2.4.13 and python 2.7

edit retag flag offensive close merge delete


BFMatcher needs keypoint descriptors to work. The goodFeaturesToTrack function only gives you strong corners, but no descriptors.

Missing gravatar imageMissing ( 2016-07-21 02:48:32 -0500 )edit

Thank you very much!

n.argirop gravatar imagen.argirop ( 2016-07-21 13:09:06 -0500 )edit