Symmetric Stereo Matching for Occlusion Handling
Authors:
- Sing Bing KangSKSing Bing Kang
- Heung-Yeung ShumHSHeung-Yeung Shum
- 27 July 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (10636919) , 399-406
Abstract
In this paper, we propose a symmetric stereo model to handle occlusion in dense two-frame stereo. Our occlusion reasoning is directly based on the visibility constraint that is more general than both ordering and uniqueness constraints used in previous work. The visibility constraint requires occlusion in one image and disparity in the other to be consistent. We embed the visibility constraint within an energy minimization framework, resulting in a symmetric stereo model that treats left and right images equally. An iterative optimization algorithm is used to approximate the minimum of the energy using belief propagation. Our stereo model can also incorporate segmentation as a soft constraint. Experimental results on the Middlebury stereo images show that our algorithm is state-of-the-art.Keywords
This publication has 18 references indexed in Scilit:
- A layered stereo algorithm using image segmentation and global visibility constraints2005
- Wide-baseline stereo from multiple views: a probabilistic account2004
- Stereo correspondence with slanted surfaces:critical implications of horizontal slant2004
- Comparison of graph cuts with belief propagation for stereo, using identical MRF parameters2003
- A global matching framework for stereo computation2002
- Computing visual correspondence with occlusions using graph cuts2002
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence AlgorithmsInternational Journal of Computer Vision, 2002
- A cooperative algorithm for stereo matching and occlusion detectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Large Occlusion StereoInternational Journal of Computer Vision, 1999
- Cooperative Computation of Stereo DisparityScience, 1976