OpenCV OrbFeatureDetector's detect function has a parameter nFeatures which tells the function what is the maximum number of keypoints to be detected.
I know more points means more comparisons when matching so less performance, while less means less accuracy.
Is there a recommended number of keypoints that gives me a good accuracy/performance relation? And if there is, why?
Depends on the application. Also, it depends on the specific image (a lot of texture and corners vs. a smooth image). I think a better approach would be to detect a large number of keypoints and delete all the keypoints with response below a threshold.
Yes that's what I normally do. With 1500 (as is done in OpenCV examples) and then thresholding, but I've seen some posts recommending 300-400 points. So, I was wondering if there's some kind of standard or recommended values. ORB's paper doesn't say anything about it
Asked: 2014-06-16 10:04:07 -0600
Seen: 577 times
Last updated: Jun 16 '14
