Ask Your Question
0

Would the source code of learning the ORB feature be provided?

asked 2018-01-03 03:56:15 -0500

I am working on re-train the ORB feature using my own database.

The pre-trained ORB descriptor is provided in static int bit_pattern_31_[256*4] in file opencv/modules/features2d/src/orb.cpp

Would the source code of learning the ORB feature be provided in the future?

Thanks a lot!

edit retag flag offensive close merge delete

Comments

Maybe you can try to ask the paper authors for the training code?

Eduardo gravatar imageEduardo ( 2018-01-03 13:53:36 -0500 )edit

1 answer

Sort by » oldest newest most voted
1

answered 2018-01-03 04:10:56 -0500

berak gravatar image

updated 2018-01-03 04:16:06 -0500

this highly unlikely, imho no such code exists in the opencv code base. you'll have to do with the algorithm description from

Rublee, Ethan, et al. “ORB: an efficient alternative to SIFT or SURF.” Computer Vision (ICCV), 2011 IEEE International Conference on. IEEE, 2011.‏

4.3. Learning Good Binary Features

To recover from the loss of variance in steered BRIEF, and to reduce correlation among the binary tests, we de- velop a learning method for choosing a good subset of bi- nary tests. One possible strategy is to use PCA or some other dimensionality-reduction method, and starting from a large set of binary tests, identify 256 new features that have high variance and are uncorrelated over a large training set.

However, since the new features are composed from a larger number of binary tests, they would be less efficient to com- pute than steered BRIEF. Instead, we search among all pos- sible binary tests to find ones that both have high variance (and means close to 0.5), as well as being uncorrelated.

The method is as follows. We first setup a training set of some 300k keypoints, drawn from images in the PASCAL 2006 set [8]. We also enumerate all possible binary tests drawn from a 31×31 pixel patch.

Each test is a pair of 5×5 sub-windows of the patch. If we note the width of our patch as wp=31 and the width of the test sub-window as wt= 5, then we have N= (wp−wt)^2 possible sub-windows. We would like to select pairs of two from these, so we have (N 2) binary tests.

We eliminate tests that overlap, so we end up with M= 205590 possible tests. The algorithm is:

  1. Run each test against all training patches.
  2. Order the tests by their distance from a mean of 0.5, forming the vector T.
  3. Greedy search:

    a. Put the first test into the result vector R and re- move it from T.

    b. Take the next test from T, and compare it against all tests in R. If its absolute correlation is greater than a threshold, discard it; else add it to R.

    c. Repeat the previous step until there are 256 tests in R. If there are fewer than 256, raise the thresh- old and try again.

This algorithm is a greedy search for a set of uncorrelated tests with means near 0.5. The result is called rBRIEF.

edit flag offensive delete link more

Comments

1

My implementation still has some issue now.

I will double check my code and create another thread if there's other questions.

Thank you.

yogurtsea gravatar imageyogurtsea ( 2018-01-03 08:40:53 -0500 )edit
Login/Signup to Answer

Question Tools

1 follower

Stats

Asked: 2018-01-03 03:56:15 -0500

Seen: 297 times

Last updated: Jan 03 '18