Similarity Measure for Corner Redetection
Corners are important image-features for tracking applications. We present a new method to calculate the similarity of corners, which is used to improve the redetection performance of corner-based tracking applications. It is a simple and fast method to calculate a scaled measure of similarity, which aggregates basic corner features like dihedral angle, cornerness, and corner orientation. Experimental results verify that the similarity measure is well suited for tracking applications.
- 1.Manmohan K. Chandraker, Christoph Stock, and Axel Pinz. Real-time camera pose in a room. In 3rd Intern. Conference on Computer Vision Systems, ICVS 2003, pages 98–110, Graz, Austria, April 2003.Google Scholar
- 2.C. Harris and M. Stephens. A combined corner and edge detector. In Proc. of the 4th Alvey Vision Conference, pages 189–192, Manchester, 1988.Google Scholar
- 3.J. Bigun and G. H. Granlund. Optimal orientation detection of linear symmetry. In ICCV, volume 1, pages 433–438, London, June 1987.Google Scholar
- 9.P. Smith, D. Sinclair, R. Cipolla, and K. Wood. Effective corner matching. In Proc. 9th British Machine Vision Conference, BMVC 1998, pages 545–556, Southampton, September 1998.Google Scholar
- 10.Ch. Stock, U. Mühlmann, M. K. Chandraker, and A. Pinz. Subpixel corner detection for tracking applications using CMOS camera technology. In Proc. of 26th Workshop of the Austrian Association for Pattern Recognition(ÖAGM/AAPR), volume 160, pages 191–199, Graz, Austria, September 2002.Google Scholar