Abstract
We address the fundamental problem of matching two static images. Significant progress has been made in this area, but the correspondence problem has not been solved. Most of the remaining difficulties are caused by occlusion and lack of texture. We propose an approach that addresses these difficulties within a perceptual organization framework, taking into account both binocular and monocular sources of information. Geometric and color information from the scene is used for grouping, complementing each other’s strengths. We begin by generating matching hypotheses for every pixel in such a way that a variety of matching techniques can be integrated, thus allowing us to combine their particular advantages. Correct matches are detected based on the support they receive from their neighboring candidate matches in 3-D, after tensor voting. They are grouped into smooth surfaces, the projections of which on the images serve as the reliable set of matches. The use of segmentation based on geometric cues to infer the color distributions of scene surfaces is arguably the most significant contribution of our research. The inferred reliable set of matches guides the generation of disparity hypotheses for the unmatched pixels. The match for an unmatched pixel is selected among a set of candidates as the one that is a good continuation of the surface, and also compatible with the observed color distribution of the surface in both images. Thus, information is propagated from more to less reliable pixels considering both geometric and color information. We present results on standard stereo pairs.
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.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IJCV 47, 7–42 (2002)
Kanade, T., Okutomi, M.: A stereo matching algorithm with an adaptive window: Theory and experiment. PAMI 16, 920–932 (1994)
Veksler, O.: Fast variable window for stereo correspondence using integral images. In: CVPR 2003, vol. I, pp. 556–561 (2003)
Belhumeur, P., Mumford, D.: A bayesian treatment of the stereo correspondence problem using half-occluded regions. In: CVPR 1992, pp. 506–512 (1992)
Geiger, D., Ladendorf, B., Yuille, A.: Occlusions and binocular stereo. IJCV 14, 211–226 (1995)
Birchfield, S., Tomasi, C.: Depth discontinuities by pixel-to-pixel stereo. In: ICCV 1998, pp. 1073–1080 (1998)
Bobick, A., Intille, S.: Large occlusion stereo. IJCV 33, 1–20 (1999)
Ishikawa, H., Geiger, D.: Occlusions, discontinuities, and epipolar lines in stereo. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, pp. 232–248. Springer, Heidelberg (1998)
Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions via graph cuts. In: ICCV 2001, vol. II, pp. 508–515 (2001)
Luo, A., Burkhardt, H.: An intensity-based cooperative bidirectional stereo matching with simultaneous detection of discontinuities and occlusions. IJCV 15, 171–188 (1995)
Zitnick, C., Kanade, T.: A cooperative algorithm for stereo matching and occlusion detection. PAMI 22, 675–684 (2000)
Zhang, Y., Kambhamettu, C.: Stereo matching with segmentation-based cooperation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. II: 556–571. Springer, Heidelberg (2002)
Scharstein, D., Szeliski, R.: Stereo matching with nonlinear diffusion. IJCV 28, 155–174 (1998)
Sun, J., Shum, H., Zheng, N.: Stereo matching using belief propagation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. II: 510–524. Springer, Heidelberg (2002)
Szeliski, R., Scharstein, D.: Symmetric sub-pixel stereo matching. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. II: 525–540. Springer, Heidelberg (2002)
Zhang, Z., Shan, Y.: A progressive scheme for stereo matching. In: Pollefeys, M., Van Gool, L., Zisserman, A., Fitzgibbon, A.W. (eds.) SMILE 2000. LNCS, vol. 2018, pp. 68–85. Springer, Heidelberg (2001)
Birchfield, S., Tomasi, C.: Multiway cut for stereo and motion with slanted surfaces. In: ICCV 1999, pp. 489–495 (1999)
Tao, H., Sawhney, H., Kumar, R.: A global matching framework for stereo computation. In: ICCV 2001, pp. I: 532–539 (2001)
Lin, M., Tomasi, C.: Surfaces with occlusions from layered stereo. In: CVPR 2003, vol. I, pp. 710–717 (2003)
Lee, M., Medioni, G., Mordohai, P.: Inference of segmented overlapping surfaces from binocular stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 824–837 (2002)
Mordohai, P., Medioni, G.: Perceptual grouping for multiple view stereo using tensor voting. In: ICPR 2002, vol. III, pp. 639–644 (2002)
Scharstein, D., Szeliski, R.: High-accuracy stereo depth maps using structured light. In: CVPR 2003, vol. I, pp. 195–202 (2003)
Medioni, G., Lee, M., Tang, C.: A Computational Framework for Segmentation and Grouping. Elsevier, Amsterdam (2000)
Sara, R.: Finding the largest unambiguous component of stereo matching. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 900–914. Springer, Heidelberg (2002)
Veksler, O.: Dense features for semi-dense stereo correspondence. IJCV 47, 247–260 (2002)
Veksler, O.: Extracting dense features for visual correspondence with graph cuts. In: CVPR 2003, pp. I: 689–694 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mordohai, P., Medioni, G. (2004). Stereo Using Monocular Cues within the Tensor Voting Framework. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3024. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24673-2_47
Download citation
DOI: https://doi.org/10.1007/978-3-540-24673-2_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21981-1
Online ISBN: 978-3-540-24673-2
eBook Packages: Springer Book Archive