Here was my test on feature matching with ORB. In the video, the target image was shown in the left side and the real-time video was in the up-right corner.
The feature points on the target image matched to the target when there were no other textured objects. If any object has detected feature points, however, the matching relationship would be disturbed significantly.
I have not test the matching approach by using SURF or SIFT features. This will be the next step.
Furthermore, I will try to apply findHomography() and getPerspectiveTransform() to find the correct object.
Hi i see your project going well, i just make similar matching project with OpenCV ORB..
ReplyDeletei use FAST, ORB in feature extractor and then i matched that descriptor with FLANNbased algorithm.
but in this case it tooks more time then SIFT descriptor.
so i want to ask which algorithm did you use at this project.