There are several kinds of detectors and descriptors, like SIFT, SURF, FAST. I wonder are they all eligible for real-time applications? Which is the best or better?

And furthermore, is Harris-Laplacian dectector still useful when we already have the above three? Is it better than them?


I think SURF is better than all , as its clear from its name , Speed Up robust Feature Detector , but its not free to use , its a patent , so you can't use it for your commercial uses , you can only use it for your studies and knowledge purpose , but i think its also depend on your app that algo to use , but surf is better with speed

  • $\begingroup$ What about Harris-Laplacian? It's not a good choice for real-time application, right? $\endgroup$ – avocado Aug 26 '13 at 11:42
  • $\begingroup$ Harris-Laplacian performs best in scale invariance ,i think your right , but i didn't use harris laplacian $\endgroup$ – ARG Aug 26 '13 at 13:07
  • 1
    $\begingroup$ Perform best? Really? Any proof? $\endgroup$ – avocado Aug 26 '13 at 13:37
  • $\begingroup$ @loganecolss its depend on your use , you can read about it here : http://www-scf.usc.edu/~boqinggo/Feature.htm and as i stated above i didn't use it , thats why i didn't describe it in my answer $\endgroup$ – ARG Aug 26 '13 at 18:22

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.