In the articles of both FREAK and BRISK, they are talking about accelerating the matching process with vectorization. And if you download the FREAK code for example from github, you'll find a trace of that in 2 files : freak_demo.cpp and hammingseg.h. How can I adapt them in order to be able to integrate the code of hammingseg.h with opencv code? Have anyone of you done that?
Unfortunately you need to use OpenCV's BFMatcher with the provided Hamming norm - I guess OpenCV's version of it is somewhat optimized but probably not as much as hammingseg.h is. It isn't possible anymore that you can write and use your own matching function without much work (which is really pitty and I still can't see the advantage of the current version to the old one, but I doubt that it will change back). Several OpenCV releases earlier (before the revision of BruteforceMatcher to BFMatcher) it was very easy to use own or other distance/norm functions like this very specialized hamming-matching.
Asked: 2014-08-30 14:47:52 -0600
Seen: 298 times
Last updated: Sep 01 '14
