A Stereo Matching Algorithm with Support Regions Based on Color and Texture Estimate

Abstract:

A stereo matching algorithm with support regions based on color and texture estimate is proposed. Firstly, the initial support regions are selected from the image according to the distribution of the quantized color labels. Then, the texture similarity is used to determine the arm length growing and combine adjacent regions. The accurate support regions are obtained. Thirdly, the support weight is introduced under the constraint of support region. Finally, the initial disparity can be corrected by using disparity adjustment method until a reasonable disparity map is obtained. The experimental results show that the good disparity result can be obtained.

• Periodical: Advanced Materials Research (Volumes 433-440)
• Pages: 3656-3661
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.433-440.3656
• Online since: January 2012
• Authors: Cheng Hui Zhu, Qi Yi Jiao, Jian Ping Wang, Xiao Bing Xu
• Keywords: Color Labels, Disparity Adjustment, Stereo Matching, Support Regions, Support Weight, Texture Similarity

References

[1] Kanade T, Okutomi M. A Stereo Matching Algorithm with an Adaptive Window Theory and Experiment [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1994, 16(9): 920-932.

DOI: 10.1109/34.310690

[2] Roberto F V, Trucco E. Efficient Stereo with Multiple Windowing[C]/Proc. of IEEE Conference on Computer Vision and Pattern Recognition. [S. l. ]: IEEE Computer Society Press, (1997).

DOI: 10.1109/cvpr.1997.609428

[3] S. B. Kang, R. Szeliski, and J. Chai, Handling occlusions in dense multi-view stereo, in Proc. IEEE Conf. Comput. Vision Pattern Recognition, vol. 1, 2001, p.103–110.

DOI: 10.1109/cvpr.2001.990462

[4] Chan S, Wong Y, and Danie J. Dense Stereo Correspondence Based on Recursive Adaptive Size Multi-Windowing[C]/Image and Vision Computing New Zealand 2003, Massey University, Palmerston North, New Zealand , 2003 . November 26-28 , 1: 256-260.

[5] VEKSLER O. Fast variable window for stereo correspondence using integral image[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Madison, WI, USA, 2003: 556-561.

DOI: 10.1109/cvpr.2003.1211403

[6] K. Zhang, J. Lu, and G. Lafruit, Cross-based local stereo matching using orthogonal integral images, IEEE TCSVT, to appear.

[7] Ojala T, Pietikainen M, Maenpaa T. Multirere solution Gray Sale and Rotation Invariant Texture Classification with local Binary Patterns. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987.

DOI: 10.1109/tpami.2002.1017623

[8] Deng Y, Manjunath B S. Unsupervised Segmentation of Color-Texture Regions in Image sand Video. IEEE Trans on Pattern Analysis and Machine Intelligence, 2001, 23(8): 800-810.

DOI: 10.1109/34.946985

[9] Gu Zheng, Su Xianyu. An Algorithm Based on Adaptive Support-Weight and Disparity Adjustment for Trinocular Stereo-Matching [J]. ACTA OPTICA SINICA, 2008, 28(4): 734-738. (in Chinese).

DOI: 10.3788/aos20082804.0734

[10] Kuk-jin Yoon, In So Kweon. Adaptive support-weight approach for correspondence search[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(4): 650-656.

DOI: 10.1109/tpami.2006.70

[11] SC HA RSTEIN D, SZEL IS KI R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms [J]. International Journal of Computer Vision, 2002, 47(1-3): 7-42.