Stereo matching based on color and disparity segmentation by belief propagation
Authors:
- 1 April 2007
- journal article
- Published by SPIE-Intl Soc Optical Eng in Optical Engineering
- Vol. 46 (4) , 043203-043203-8
Abstract
Segment-based stereo matching algorithms are not able to deal with the difficulty that disparity boundaries appear inside the initial color segments. To solve this problem, we propose a novel algorithm that segments the reference image by combining color and depth segmentation information. Then we construct the energy function in segment domain, which embodies the smoothness and visibility constraints to penalize the discontinuities of edge pixels and potential occluded regions, respectively. Finally, the optimal disparity plane labeling is approximated by applying loopy belief propagation. Experimental results on the benchmark images demonstrate that our algorithm is comparable to the state-of-the-art algorithms.Keywords
This publication has 13 references indexed in Scilit:
- A layered stereo algorithm using image segmentation and global visibility constraints2005
- Graph-based surface reconstruction from stereo pairs using image segmentation2005
- A symmetric patch-based correspondence model for occlusion handling2005
- Segment-based stereo matching using graph cuts2004
- Advances in computational stereoIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- A global matching framework for stereo computation2002
- Mean shift: a robust approach toward feature space analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Stereo Matching with Segmentation-Based Cooperation2002
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence AlgorithmsInternational Journal of Computer Vision, 2002
- A pixel dissimilarity measure that is insensitive to image samplingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998