Ambiguous Region Matching and Boundary Pixel Optimization for Stereo Computation

Abstract:

In this paper, we present a stereo matching algorithm based on planar surface hypothesis. It improves the results of low texture regions and mixed pixels on object boundaries. First, regions are segmented by applying the mean-shift segmentation method. Then we propose a coarse-to-fine algorithm to increase the reliable correspondences in low texture regions. Third, the Belief Propagation algorithm is used to optimize disparity plane labeling. Finally, for a mixed pixel, we utilize the results of the depth plane and the local region of it to regulate its disparity. Experimental results using the Middlebury stereo test show that the performance of our method is high.

• Periodical: Advanced Materials Research (Volumes 546-547)
• Pages: 735-740
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.546-547.735
• Online since: July 2012
• Authors: Xing Nian Cui, Fan Yang, Qing Min Liao
• Keywords: Belief Propagation, Dense Disparity Map, Mean-Shift, Mixed Pixel, Stereo Matching

References

[1] Nguyen H. T. and Minh N. Do, Image-based Rendering with Depth Information Using the Propagation Algorithm[C], Proceedings of Acoustics, Speech and Signal Processing, USA, 2005, pp.589-592.

DOI: 10.1109/icassp.2005.1415473

[2] H. Tao, H. Sawhney, and R. Kumar, A global matching framework for stereo computation, In ICCV, 2001, pp.532-539.

[3] Andreas Klaus, Mario Sormann, and Konrad Karner, Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure, In ICPR, 2006, pp.15-18.

DOI: 10.1109/icpr.2006.1033

[4] J. Sun, Y. Li, S. Kang, and H. Shum, Symmetric stereo matching for occlusion handling, In CVPR, 2005, p.399–406.

DOI: 10.1109/cvpr.2005.337

[5] Heiko Hirschmuller, Improvements in Real-Time Correlation-Based Stereo Vision, In S MBV, 2001, pp.141-148.

DOI: 10.1109/smbv.2001.988772

[6] P. F. Felzenszwalb and D. P. Huttenlocher, Efficient belief propagation for early vision, In CVPR, 2004, p.261–268.

[7] T. Kanade and M. Okutomi, A stereo matching algorithm with an adaptive window: theory and experiment, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, pp.920-932, Sep. (1994).

DOI: 10.1109/34.310690

[8] Dominik M. Aufderheide, Markus Steffens, Stephan Kieneke and Werner Krybus, Texture Analysis for Adopting of Correlation Windows In Stereo Correspondence, In ICVIP, 2009, pp.229-234.

[9] S. W. Hasinoff, S. B. Kang, and R. Szeliski, Boundary matting for view synthesis, In CVIU, 2006, pp.22-32.

[10] Yuichi Taguchi, Bennett Wilburn, and C. Lawrence Zitnick, Stereo Reconstruction with Mixed Pixels Using Adaptive Over-Segmentation, In CVPR, 2008, pp.1-8.

DOI: 10.1109/cvpr.2008.4587691

[11] M. Bleyer and M. Gelautz, A layered stereo algorithm using image segmentation and global visibility constraints, In ICIP, 2004, pp.297-300.

DOI: 10.1109/icip.2004.1421743

[12] F. Zhou, W. Yang, and Q. Liao, A coarse-to-fine subpixel registration method to recover local perspective deformation in the application of image super-resolution, IEEE Trans. Image Process, vol. 21, no. 1, p.53–66, Jan. (2012).

DOI: 10.1109/tip.2011.2159731

[13] M. Bleyer and M. Gelautz, A layered stereo matching algorithm using image segmentation and global visibility constraints, in ISPRS, 59(3), p.128–150, May (2005).

DOI: 10.1016/j.isprsjprs.2005.02.008

[14] D. Scharstein and R. Szeliski, A taxonomy and evaluation of dense two-frame stereo correspondence algorithms, In IJCV, 47(1/2/3): 7-42, April-June (2002).

DOI: 10.1109/smbv.2001.988771

[15] H. Hirschmüller and D. Scharstein, Evaluation of cost functions for stereo matching, In CVPR, 2007, pp.1-8.

[16] A. Berman, P. Vlahos and A. Dadourian, Comprehensive method for removing from an image the back-ground surrounding a selected object, U.S., Patent No. 6, 134, 346, (2000).