1

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 tried using homography detector. 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=133Nbo46bgwt7Q4IT2RDuPVR67TX9xG6F

lazyadt
  • 13
  • 6

1 Answers1

2

This a very common problem. Because images like this, they actually do not have much in common. The overlap region is not rich in feature. What you can do is dig into opencv stitcher code and there they use confidence factor for feature matching, you can play with that confidence factor to get matches in this case. But this will only work if your feature detector is able to detect some features in overlapping resion.

You can also look at this post: Related Question

It might be helpful for you.

"OpenCV stitching code"

This is full pipleline of OPencv Stitching code. You can see that there are lot of parameters you can change to make your code give some good stitching result. Also I would suggest using a small image (640 X480) for the feature detection step. Using small images is better than using very large images

Garvita Tiwari
  • 584
  • 2
  • 12
  • The stitching_detailed code is what I'm using. In the link you provided, you suggested changing the rotation matrix of the camera. Can you please tell me how exactly to do that. – lazyadt May 18 '18 at 06:55
  • That is if you know the relative rotation between camera from some other sources than images features.RIght now, you can just play with all the paramteters in the code and you will get good results, although it might not work always – Garvita Tiwari May 18 '18 at 06:59
  • Alright, thank you. From what I gather is that you are suggesting me play around with the match_conf feature. Is that correct? – lazyadt May 18 '18 at 07:08
  • Yes, since I had camera rotation with me, when I was working on the same thing, so I was able to get rough overlapping area. Maybe you can generalise something like this to your problem also. – Garvita Tiwari May 18 '18 at 07:36