Stable Monotonic Matching for Stereoscopic Vision
This paper deals with stable monotonic matching (SMM), which is a generalization of stable matching that includes ordering constraint. The matching algorithm is fast, does not optimize any explicit cost functional, processes one epipolar line at a time, and requires only two parameters for disparity search range.
A designed experiment demonstrates that SMM has no occluding boundary artifacts, that it detects half-occluded regions reliably even if they are wide, and that it rarely misses thin objects in the foreground, unless the ordering is violated. On the other hand, the resulting disparity map is often not dense, especially in weakly textured areas.
KeywordsStable Match Stereo Match Maximum Cardinality Epipolar Line Stereoscopic Vision
Unable to display preview. Download preview PDF.
- 2.Y. Boykov, O. Veksler, R. Zabih: Disparity component matching for visual correspondence. In: Proceed. Conf. Computer Vision and Pattern Recognition, (1997) 470–475. 184Google Scholar
- 6.H. Ishikawa and D. Geiger. Occlusions, discontinuities, and epipolar lines in stereo. In: Proceed. European Conference on Computer Vision, vol. 1 (1998) 232–248. 184Google Scholar
- 8.L. Robert, R. Deriche: Dense depth map reconstruction: A minimization and regularization approach which preserves discontinuities. In: Proc. Int. Conf. Image Processing, (1992) 123–127. 184Google Scholar
- 9.S. Roy, I. J. Cox: A maximum-flow formulation of the n-camera stereo correspondence problem. In: Internat. Conf. Proc. Computer Vision, (1998) 492–499. 184Google Scholar
- 10.R. Šára: The class of stable matchings for computational stereo. Research Report CTU-CMP-1999-22, Center for Machine Perception, Czech Technical University, Prague, Czech Republic, (1999). 185, 187, 1Google Scholar
- 11.R. Sedgewick: Algorithms. Addison-Wesley, 2nd edition, (1988). 187Google Scholar