Abstract
We present an algorithm to reduce per-pixel search ranges for Markov Random Fields-based stereo algorithms. Our algorithm is based on the intuitions that reliably matched pixels need less regularization in the energy minimization and neighboring pixels should have similar disparity search ranges if their pixel values are similar. We propose a novel bi-labeling process to classify reliable and unreliable pixels that incorporate left-right consistency checks. We then propagate the reliable disparities into unreliable regions to form a complete disparity map and construct per-pixel search ranges based on the difference between the disparity map after propagation and the one computed from a winner-take-all method. Experimental results evaluated on the Middlebury stereo benchmark show our proposed algorithm is able to achieve 77% average reduction rate while preserving satisfactory accuracy.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Scharstein, D., Szeliski, R.: vision.middlebury.edu/stereo/
Sun, J., Zheng, N.N., Shum, H.Y.: Stereo matching using belief propagation. IEEE Trans. on Pattern Analysis and Machine Intelligence 25(7), 787–800 (2003)
Boykov, Y., Veksler, O., Zabih, R.: Markov random fields with efficient approximations. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 648–657 (1998)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. on Pattern Analysis and Machine Intelligence 23(11), 1222–1239 (2001)
Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Trans. on Pattern Analysis and Machine Intelligence 26(9), 1124–1137 (2004)
Bobick, A.F., Intille, S.S.: Large occlusion stereo. Int. J. of Computer Vision, 181–200 (November 1999)
Egnal, G., Wildes, R.P.: Detecting binocular half-occlusions: empirical comparisons of five approaches. IEEE Trans. on Pattern Analysis and Machine Intelligence 24(8), 1127–1133 (2002)
Levin, A., Lischinski, D., Weiss, Y.: Colorization using optimization. In: Proc. of ACM SIGGRAPH, pp. 689–694 (August 2004)
Veksler, O.: Reducing search space for stereo correspondence with graph cuts. In: British Machine Vision Conf., vol. 2, pp. 709–718 (2006)
Yu, T., Lin, R.S., Super, B., Tang, B.: Efficient message representations for belief propagation. In: Proc. of Intl. Conf. on Computer Vision (2007)
Gong, M., Yang, Y.H.: Fast unambiguous stereo matching using reliability-based dynamic programming. IEEE Trans. on Pattern Analysis and Machine Intelligence 27(6), 998–1003 (2005)
Sara, R.: Finding the largest unambiguous component of stereo matching. In: Proc. of Europ. Conf. on Computer Vision, pp. 900–914 (2002)
Veksler, O.: Extracting dense features for visual correspondence with graph cuts. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, vol. 1, pp. 689–694 (2003)
Cech, J., Sara, R.: Efficient sampling of disparity space for fast and accurate matching. In: Intl. Workshop on Benchmarking Automated Calibration, Orientation, and Surface Reconstruction from Images (2007)
Zhang, Z., Shan, Y.: A progressive scheme for stereo matching. In: Europ. Workshop on 3D Structure from Multiple Images of Large-Scale Environments (July 2000)
Szeliski, R., Zabih, R., Scharstein, D., Veksler, O., Kolmogorov, V., Agarwala, A., Tappen, M.F., Rother, C.: A comparative study of energy minimization methods for markov random fields. In: Proc. of Europ. Conf. on Computer Vision, vol. 2, pp. 19–26 (2006)
Birchfield, S., Tomasi, C.: A pixel dissimilarity measure that is insensitive to image sampling. IEEE Trans. on Pattern Analysis and Machine Intelligence 20(4), 401–406 (1998)
Wang, L., Liao, M., Gong, M., Yang, R.: High-quality real-time stereo using adaptive cost aggregation and dynamic programming. In: Intl. Symposium on 3D Data Processing, Visualization and Transmission, pp. 798–805 (2006)
Yoon, K.J., Kweon, I.S.: Locally adaptive support-weight approach for visual correspondence search. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 924–931 (2005)
Yang, Q., Wang, L., Yang, R., Stewenius, H., Nister, D.: Stereo matching with color-weighted correlation, hierachical belief propagation and occlusion handling. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 2347–2354 (2006)
Hirschmuller, H., Scharstein, D.: Evaluation of cost functions for stereo matching. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (2007)
Scharstein, D., Pal, C.: Learning conditional random fields for stereo. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (2007)
Press, W., Flannery, B., Teukolsky, S., Vetterling, W.: Numerical recipes inc. (1988)
Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. on Pattern Analysis and Machine Intelligence 22(8), 888–905 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, L., Jin, H., Yang, R. (2008). Search Space Reduction for MRF Stereo. In: Forsyth, D., Torr, P., Zisserman, A. (eds) Computer Vision – ECCV 2008. ECCV 2008. Lecture Notes in Computer Science, vol 5302. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88682-2_44
Download citation
DOI: https://doi.org/10.1007/978-3-540-88682-2_44
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88681-5
Online ISBN: 978-3-540-88682-2
eBook Packages: Computer ScienceComputer Science (R0)