0
$\begingroup$

What is the difference between a feature detector and a dense detector in computer vision? Are they the same or a subset of one another?

For the following algorithms (implemented in OpenCV), which of them are feature detectors and/or dense detectors?

  • SIFT
  • SURF
  • AGAST
  • KAZE
  • AKAZE
  • FAST
  • BRISK
  • ORB
  • GFTT
  • HarrisLaplace
  • StarDetector
$\endgroup$
  • $\begingroup$ I know what a feature detector is (roughly so), but what's a dense detector? Can you link to a usage of that term? $\endgroup$ – Marcus Müller Jun 27 at 0:16
  • $\begingroup$ I was reading this paper and the authors mention Dense Detector, even in other papers they mention Dense Feature Detector. And, I've already googled but didn't find any concrete answer. $\endgroup$ – paul-shuvo Jun 27 at 0:25
1
$\begingroup$

For class matching, Hietanen in [29] compares several binary descriptors and SIFT with different detectors, including a dense grid. SIFT preformed better than other descriptors and dense grid responds very well.

This result leads us to test dense detector for different descriptors…

It seems that a dense detector is one that uses a dense grid on which to evaluate some feature metric.

This is opposed to "classical" feature detectors that search the image for points with features.

Frankly, spanning a grid over an image to reduce it to a lower resolution does sound like what I'd call a subsampling and image transform, but maybe I'm misunderstanding this!

| improve this answer | |
$\endgroup$

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.