Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling

Yáng Qìngxióng; Wang Liang; Yang Ruigang; Henrik Stewénius; David Nistér

doi:10.1109/CVPR.2006.292

Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling

Yáng Qìngxióng, Wang Liang, Yang Ruigang, Henrik Stewénius, David Nistér

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

121 Scopus citations

Abstract

In this paper, we formulate an algorithm for the stereo matching problem with careful handling of disparity, discontinuity and occlusion. The algorithm works with a global matching stereo model based on an energy-minimization framework. The global energy contains two terms, the data term and the smoothness term. The data term is first approximated by a color-weighted correlation, then refined in occluded and low-texture areas in a repeated application of a hierarchical loopy belief propagation algorithm. The experimental results are evaluated on the Middlebury data set, showing that our algorithm is the top performer.

Original language	English
Title of host publication	Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Pages	2347-2354
Number of pages	8
DOIs	https://doi.org/10.1109/CVPR.2006.292
State	Published - 2006
Event	2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 - New York, NY, United States Duration: Jun 17 2006 → Jun 22 2006

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2
ISSN (Print)	1063-6919

Conference

Conference	2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Country/Territory	United States
City	New York, NY
Period	6/17/06 → 6/22/06

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2006.292

Cite this

Qìngxióng, Y., Liang, W., Ruigang, Y., Stewénius, H., & Nistér, D. (2006). Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling. In Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 (pp. 2347-2354). Article 1641041 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2). https://doi.org/10.1109/CVPR.2006.292

Qìngxióng, Yáng ; Liang, Wang ; Ruigang, Yang et al. / Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling. Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. 2006. pp. 2347-2354 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

@inproceedings{c99934474e1e4fe2a4e43aed24a11277,

title = "Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling",

abstract = "In this paper, we formulate an algorithm for the stereo matching problem with careful handling of disparity, discontinuity and occlusion. The algorithm works with a global matching stereo model based on an energy-minimization framework. The global energy contains two terms, the data term and the smoothness term. The data term is first approximated by a color-weighted correlation, then refined in occluded and low-texture areas in a repeated application of a hierarchical loopy belief propagation algorithm. The experimental results are evaluated on the Middlebury data set, showing that our algorithm is the top performer.",

author = "Y{\'a}ng Q{\`i}ngxi{\'o}ng and Wang Liang and Yang Ruigang and Henrik Stew{\'e}nius and David Nist{\'e}r",

year = "2006",

doi = "10.1109/CVPR.2006.292",

language = "English",

isbn = "0769525970",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

pages = "2347--2354",

booktitle = "Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006",

note = "2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 ; Conference date: 17-06-2006 Through 22-06-2006",

}

Qìngxióng, Y, Liang, W, Ruigang, Y, Stewénius, H & Nistér, D 2006, Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling. in Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006., 1641041, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 2347-2354, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, New York, NY, United States, 6/17/06. https://doi.org/10.1109/CVPR.2006.292

Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling. / Qìngxióng, Yáng; Liang, Wang; Ruigang, Yang et al.
Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. 2006. p. 2347-2354 1641041 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling

AU - Qìngxióng, Yáng

AU - Liang, Wang

AU - Ruigang, Yang

AU - Stewénius, Henrik

AU - Nistér, David

PY - 2006

Y1 - 2006

N2 - In this paper, we formulate an algorithm for the stereo matching problem with careful handling of disparity, discontinuity and occlusion. The algorithm works with a global matching stereo model based on an energy-minimization framework. The global energy contains two terms, the data term and the smoothness term. The data term is first approximated by a color-weighted correlation, then refined in occluded and low-texture areas in a repeated application of a hierarchical loopy belief propagation algorithm. The experimental results are evaluated on the Middlebury data set, showing that our algorithm is the top performer.

AB - In this paper, we formulate an algorithm for the stereo matching problem with careful handling of disparity, discontinuity and occlusion. The algorithm works with a global matching stereo model based on an energy-minimization framework. The global energy contains two terms, the data term and the smoothness term. The data term is first approximated by a color-weighted correlation, then refined in occluded and low-texture areas in a repeated application of a hierarchical loopy belief propagation algorithm. The experimental results are evaluated on the Middlebury data set, showing that our algorithm is the top performer.

UR - http://www.scopus.com/inward/record.url?scp=33845598031&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845598031&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2006.292

DO - 10.1109/CVPR.2006.292

M3 - Conference contribution

AN - SCOPUS:33845598031

SN - 0769525970

SN - 9780769525976

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 2347

EP - 2354

BT - Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006

T2 - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006

Y2 - 17 June 2006 through 22 June 2006

ER -

Qìngxióng Y, Liang W, Ruigang Y, Stewénius H, Nistér D. Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling. In Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. 2006. p. 2347-2354. 1641041. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). doi: 10.1109/CVPR.2006.292

Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this