Revision history [back]

I've had similar problems. The matching algorithm tries to find a match for every point in the first image. If there's more keypoints than in the second image, this means, that some keypoints in the second image will be matches to more than one keypoint in the first. (This seems to be the case in your examples, too). RANSAC then sometimes finds a homography that transforms every source point to a single destination point. Try to compute the matches by having the image with the fewer keypoints in the first position. You will get less but better matches. Note: when swapping the image descriptors for matching, you will have to invert the homography matrix.

I've had similar problems. The matching algorithm tries to find a match for every point in the first image. If there's more keypoints in the first image than there is in the second image, this means, that some keypoints in the second image will be matches to more than one keypoint in the first. (This seems to be the case in your examples, too). In extreme cases (just a few keypoints in the second image) RANSAC then sometimes finds a homography that transforms every source point to a single destination point. Try to compute the matches by having the image with the fewer keypoints in the first position. You will get less but better matches. Note: when swapping the image descriptors for matching, you will have to invert the homography matrix.

I've had similar problems. The matching algorithm tries to find a match for every point in the first image. If there's more keypoints in the first image than there is in the second image, this means, that some keypoints in the second image will be matches to more than one keypoint in the first. (This seems to be the case in your examples, too). too).

In extreme cases (just a few keypoints in the second image) RANSAC then sometimes finds a homography that transforms every source point to a single destination point. Try to compute the matches by having the image with the fewer keypoints in the first position. You will get less but better matches. Note: matches.

Note: when swapping the image descriptors for matching, you will have to invert the homography matrix.