Center for Machine Perception

Czech Technical University in Prague

http://cmp.felk.cvut.cz

(suitable for cross-eyed viewing from about 15cm distance, click to download full-size rectified images)

Dense binocular stereo is a challenging problem, since the correspondence problem is generally of combinatorial complexity. Why? It has to segment the image to

*binocularly visible*regions (and to find correspondences within them),*half-occluded*regions that have no correspondence in the other image,*mutually occluded*regions, they are regions in the left image that correspond to entire regions in the right image, but within these regions no correspondence can be found. This is a quite frequent event in general scenes, in the Larch Grove Example it is the region in between the two leftmost trees.

Another way to avoid the complexity is to use different notion for
what is a good matching. We propose the game-theoretic notion of
stability. Fortunately, it is possible to define stability in a way
that (low-order) polynomial algorithm exists. **We claim stability is a
suitable and practical concept for stereoscopic matching.**

We pose the correspondence as the *confidently stable monotonic
matching problem*. Much of the matching artifacts is then
avoided. The algorithm is parameter-free except for confidence level
at which we wish to recover a matching. Results are not guaranteed to
be dense but the density is high enough for the approach to be viable.
Moreover, the density can be dramatically improved (even five-folds)
if the matching process is stratified (ongoing
work with Jana Kostkova).

assumes ordering, uses 5x5 matching window, Normalized Cross-Correlation (NCC), unmatched regions are gray, disparity is color-coded from blue (small disparity) to red (large disparity), click to get full-size disparity maps

0% of NCC range | 0.5% of NCC range |
---|---|

1.5% of NCC range | 5% of NCC range |

**Results on Standard Datasets****What is stability?**- Broader overview and definitions are in
**ECCV 2002 talk**[PDF, 5MB] - For more results and the Larch Grove Example Analysis see
**ECCV 2002 talk addendum**[PDF, 5MB]

**Finding the Largest Unambiguous Component of Stereo Matching.**R. Sara. In Proceedings 7th European Conference on Computer Vision (ECCV2002) vol. 2, pp. 900-914, Springer-Verlag LNCS 2352, May 2002. [Corrected paper, color version [PDF], Abstract+Paper (Springer)]**Sigma-Delta Stable Matching for Computational Stereopsis**R. Sara. Research Report CTU-CMP-2001-25, Center for Machine Perception, Czech Technical University, September 2001 [Sara-TR-2001-25.pdf]**The Class of Stable Matchings for Computational Stereo.**R. Sara. Research Report CTU-CMP-1999-22, Center for Machine Perception, Czech Technical University, November 1999. [Sara-TR-1999-22.pdf, 2.5MB]

Radim Sara | Last modified: Tue Jun 25 13:47:47 CEST 2002 |