Browse > Article

Bilateral Approach for Fast Stero Matching  

Ju, Myung-Ho (Dept. of Computer Eng., Catholic University of Korea)
Kang, Hang-Bong (Dept. Digital Media, Catholic University of Korea)
Publication Information
Abstract
Typically, local methods for stereo matching are fast but have relatively low degree of accuracy while global ones, though costly, can achieve a higher degree of accuracy in retrieving disparity information. Recently, some local methods like the ones based on segmentation or adaptive weights are suggested which achieve more accuracy than global ones. These newly suggested local methods that can estimate more accurate disparity information cannot be easily used since they require more computational costs which increase in proportion to the window size they use. In this paper, we propose the method by using distance weights and pixel difference weights similar to those of the bilateral filter. Specifically, we present constant time O(1) algorithm for the case the distance weights are equal. The suggested method requires constant time for computation regardless of the used window size. Furthermore, experiments show that the matching performance of our method is as good as the ones of other recent methods.
Keywords
stereo; bilateral filter; constant time;
Citations & Related Records
연도 인용수 순위
  • Reference
1 K. J. Yoon and I. S. Kweon, 'Adaptive Support-Weight Approach for Correspondence Search', IEEE Trans. PAMI, 28(4):650-656, 2006   DOI   ScienceOn
2 H. Tao, H. S. Sawhney and R. Kumar, ' Global Matching Framework for Stereo Computation', In Proc. Int'l Conf. Computer Vision, vol. 1, pp. 532-539, 2001   DOI
3 F. Porikli, 'Constant Time Bilateral Filtering', In Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008
4 Y. Xu, D. Wang, T. Feng and H.-Y. Shum, 'Stereo Computation using Radial Adaptive Windows', In Proc. Int'l Conf. Pattern Recognition, vol. 3, pp. 595-598, 2002   DOI
5 F. Tombari, S. Mattoccia and L. Di Stefano, 'Segmentation-based adaptive support for accurate stereo correspondence', In Proc. IEEE Pacific-Rim Symposium on Image and Video Technology, 2007
6 http://vision.middlebury.edu/stereo
7 O. Veksler, 'Fast Variable Window for Stereo Correspondence using Integral mages', In Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 556-561, 2003
8 O. Veksler, 'Stereo Correspondence with Compact Windows via Minimum Ratio Cycle', IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 12, pp. 1654-1660, December, 2002   DOI   ScienceOn
9 S. B. Kang, R. Szeliski and C. Jinxjang, 'Handling Occlusions in Dense Multi-View Stereo, In Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 103-110, 2001   DOI
10 F. Tombari, S. Mattoccia, L. Di Stefano and E. Addimanada, 'Near real-time stereo based on effective cost aggregation', International Conference on Pattern Recognition, December, 2008
11 L. Wang, S. B. Kang and H.-Y. Shum, 'Cooperative Segmentation and Stereo Using Perspective Space Search', In Proc. Asian Conf. Computer Vision, vol. 1, pp. 366-371, 2004
12 T. Darrel, 'A Radial Cumulative Similarity Transform for Robust Image Correspondence', In Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 656-662, 1998