cvpr cvpr2013 cvpr2013-384 cvpr2013-384-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Xing Mei, Xun Sun, Weiming Dong, Haitao Wang, Xiaopeng Zhang
Abstract: This paper presents a novel tree-based cost aggregation method for dense stereo matching. Instead of employing the minimum spanning tree (MST) and its variants, a new tree structure, ”Segment-Tree ”, is proposed for non-local matching cost aggregation. Conceptually, the segment-tree is constructed in a three-step process: first, the pixels are grouped into a set of segments with the reference color or intensity image; second, a tree graph is created for each segment; and in the final step, these independent segment graphs are linked to form the segment-tree structure. In practice, this tree can be efficiently built in time nearly linear to the number of the image pixels. Compared to MST where the graph connectivity is determined with local edge weights, our method introduces some ’non-local’ decision rules: the pixels in one perceptually consistent segment are more likely to share similar disparities, and therefore their connectivity within the segment should be first enforced in the tree construction process. The matching costs are then aggregated over the tree within two passes. Performance evaluation on 19 Middlebury data sets shows that the proposed method is comparable to previous state-of-the-art aggregation methods in disparity accuracy and processing speed. Furthermore, the tree structure can be refined with the estimated disparities, which leads to consistent scene segmentation and significantly better aggregation results.
[1] D. Comaniciu and P. Meer. Mean shift: a robust approach toward feature space analysis. PAMI, 24(5):603–619, 2002.
[2] T. H. Cormen, C. E. Leiserson, R. L. Rivest, and C. Stein. Introduction to algorithms, 3rd Edition. MIT Press, 2009.
[3] L. De-Maeztu, S. Mattoccia, A. Villanueva, and R. Cabeza. Linear stereo matching. In ICCV, pages 1708–1715, 2011.
[4] P. F. Felzenszwalb and D. P. Huttenlocher. Efficient graphbased image segmentation. IJCV, 59(2): 167–181, 2004.
[5] A. Geiger, P. Lenz, and R. Urtasun. Are we ready for autonomous driving? the kitti vision benchmark suite. In CVPR, pages 3354–3361, 2012.
[6] K. He, J. Sun, and X. Tang. Guided image filtering. In ECCV, pages 1–14, 2010.
[7] A. Hosni, M. Bleyer, M. Gelautz, and C. Rhemann. Local stereo matching using geodesic support weights. In ICIP, pages 2093–2096, 2009.
[8] A. Klaus, M. Sormann, and K. Karner. Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure. In ICPR, pages 15–18, 2006.
[9] V. Kolmogorov, A. Criminisi, A. Blake, G. Cross, and C. Rother. Bi-layer segmentation of binocular stereo video. In CVPR, pages 407–414, 2005.
[10] C. Lei, J. M. Selzer, and Y.-H. Yang. Region-tree based stereo using dynamic programming optimization. In CVPR, pages 2378–2385, 2006.
[11] X. Mei, X. Sun, M. Zhou, S. Jiao, H. Wang, and X. Zhang. On building an accurate stereo matching system on graphics hardware. In ICCV Workshops, pages 467–474, 2011.
[12] C. D. Mutto, P. Zanuttigh, and G. M. Cortelazzo. Fusion of geometry and color information for scene segmentation. IJSTSP, 6(5):505–521, 2012.
[13] X. Ren. Local grouping for optical flow. In CVPR, pages 1–8, 2008.
[14] C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. In CVPR, pages 3017–3024, 2011.
[15] D. Scharstein and R. Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IJCV, 47(1-3):7–42, 2002.
[16] D. Scharstein and R. Szeliski. Middlebury stereo evaluation, 2012. http://vision.middlebury.edu/stereo/eval/.
[17] J. Shi and J. Malik. Normalized cuts and image segmentation. PAMI, 22(8):888–905, 2000.
[18] B. M. Smith, L. Zhang, and H. Jin. Stereo matching with nonparametric smoothness priors in feature space. In CVPR, pages 485–492, 2009.
[19] F. Tombari, S. Mattoccia, L. Stefano, and E. Addimanda. Classification and evaluation of cost aggregation methods for stereo correspondence. In CVPR, pages 1–8, 2008.
[20] F. Tombari, S. Mattoccia, and L. D. Stefano. Segmentationbased adaptive support for accurate stereo correspondence. In PSIVT, pages 427–438, 2007.
[21] O. Veksler. Stereo correspondence by dynamic programming on a tree. In CVPR, pages 384–390, 2005.
[22] Z. Wang and Z. Zheng. A region based stereo matching algorithm using cooperative optimization. In CVPR, pages 1–8, 2008.
[23] Q. Yang. A non-local cost aggregation method for stereo matching. In CVPR, pages 1402–1409, 2012.
[24] Q. Yang, L. Wang, R. Yang, H. Stew e´nius, and D. Nist e´r. Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling. PAMI, 31(3):492–504, 2009.
[25] K. J. Yoon and I. S. Kweon. Adaptive support-weight approach for correspondence search. PAMI, 28(4):650–656, 2006. 333222000