Invariant Features from Interest Point Groups

Reference:

Brown, M. and Lowe, D., 2002. Invariant Features from Interest Point Groups. In: BMVC 2002: 13th British Machine Vision Conference, 2002-09-02 - 2002-09-05, Cardiff.

Related documents:

Official URL:

http://www.bmva.org/bmvc/2002/index.html

Related URLs:

• http://www.bmva.org/bmvc/2002/papers/92/full_92.pdf

Abstract

This paper approaches the problem of ¯nding correspondences between images in which there are large changes in viewpoint, scale and illumi- nation. Recent work has shown that scale-space `interest points' may be found with good repeatability in spite of such changes. Further- more, the high entropy of the surrounding image regions means that local descriptors are highly discriminative for matching. For descrip- tors at interest points to be robustly matched between images, they must be as far as possible invariant to the imaging process. In this work we introduce a family of features which use groups of interest points to form geometrically invariant descriptors of image regions. Feature descriptors are formed by resampling the image rel- ative to canonical frames de¯ned by the points. In addition to robust matching, a key advantage of this approach is that each match implies a hypothesis of the local 2D (projective) transformation. This allows us to immediately reject most of the false matches using a Hough trans- form. We reject remaining outliers using RANSAC and the epipolar constraint. Results show that dense feature matching can be achieved in a few seconds of computation on 1GHz Pentium III machines.

Export

Actions (login required)