0
$\begingroup$

In ~2006 the FAST corner detector was introduced. One of it characteristics is that you have to train a decision tree from some test image in order to learn the types of corners present and relevant in the test image. One of the consequences is that the images in which you will be applying the detector have to be somewhat similar in relation to the pose (perspective), global illumination, etc. to the test image used in the training phase.

Feature descriptors such as BRIEF and ORB make use of FAST or a modified version of FAST in their reference papers.

Then, in ~2010 the AGAST corner detection was proposed to address this issue. According to the authors, you should not have to retrain the detector on a test image (but you may if you really want to or think this is really necessary).

Then feature descriptors such as BRISK and FREAK showed up, using a modified version of AGAST in their reference papers.

My question is: Since AGAST is an evolution of FAST aimed at solving some of its issues, should someone simply use AGAST from now on when building a detection application? (I am not speaking of doing pure research on the topic of detectors)

Is there some paper proving or at least showing convincingly that you should now use AGAST? I know I could simply test them both every time I build a detection application, but honestly, if there is a relatively good point I should use AGAST, it would be time saving.

Improve this question
$\endgroup$

1 Answer 1

Reset to default
1
$\begingroup$

I am not aware of a direct comparison, other than the agast paper: http://www6.in.tum.de/Main/Publications/Mair2010c.pdf

However, Agast is also based on AST, which is developed by the authors of FAST -Edward Rosten (et al.). It is just a better training. So it might be safe to assume the improvements, based on the original Agast paper.

Moreover, here is a tracker I implemented based on Agast features:

https://www.youtube.com/watch?v=rZWu4LxmsME

This works fairly well in many cases and was able to convince me on the power of Agast (Doesn't work as good with FAST features).

Improve this answer
$\endgroup$
1
  • $\begingroup$ Ok that's what I thought. In the BRISK paper, they mention that "[w]ith the focus on efficiency of computation, our detection methodology is inspired by [AGAST], [...] essentially an extension fo accelerated performance of the now popular FAST, proven to be a very efficient basis for feature extraction." (BRISK: Binary Robust Invariant Scalable Keypoints -- Stefan Leutenegger, Margarita Chli and Roland Y. Siegwart Autonomous Systems Lab, ETH Zurich $\endgroup$
    – Doombot
    Commented Oct 14, 2014 at 13:03

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