Stitching images can't detect common feature points

asked 2018-05-18 04:40:36 -0500

I wish to stitch two or more images using OpenCV and C++. The images have regions of overlap but they are not being detected. I am using the code stitching_detailed.cpp, available at:

https://github.com/opencv/opencv/blob...

I tried using homography detector. Will using the FLANN detector help? Can someone please suggest as to what other methods I should use. Also, I wish to use the ORB algorithm, and not SIFT or SURF. The images can be found at-

https://drive.google.com/open?id=133N...

edit retag flag offensive close merge delete

Comments

ah, cool, you made it here. sorry for the previous mishap, again !

berak gravatar imageberak ( 2018-05-18 05:08:02 -0500 )edit
1

It's okay!

lazyadt gravatar imagelazyadt ( 2018-05-18 05:33:32 -0500 )edit

Descriptor method is not the problem. Scale invariance means descriptors are not sensible to scale : but there is some limits (less than 4 I cannot find a reference)

LBerger gravatar imageLBerger ( 2018-05-18 07:34:05 -0500 )edit

What do you suggest I should do?

lazyadt gravatar imagelazyadt ( 2018-05-19 02:15:46 -0500 )edit