Dense Stereo Matching Based On Propagation with Voronoi Diagram.
作者： Chengke Wu , Hung-Tat Tsui , Li Tang
DOI:
关键词: Power diagram 、 Blossom algorithm 、 Weighted Voronoi diagram 、 Matching (graph theory) 、 Centroidal Voronoi tessellation 、 Voronoi diagram 、 Artificial intelligence 、 Feature (computer vision) 、 Mathematics 、 Pattern recognition 、 Real image
摘要: A new dense matching algorithm is proposed in this paper. It based on propagation from N seed points, which have been matched reliably by feature tracking. The whole image first divided into cells the Voronoi diagram of points. Then corresponding relations are propagated each cell until all pixels within processed. Modified sum squared differences (SSD) employed as cost function according to a statistic model disparity distribution window. size window adaptive. made inversely proportional texture density inside increase reliability matching. significant merit that it can be applied wide range pairs including those with large disparities, or without rectification. has verified real images and results show both robust accurate.
iitb.ac.in 参考文章(15)
Ye Zhang, Chandra Kambhamettu, None, Stereo Matching with Segmentation-Based Cooperation european conference on computer vision. pp. 556- 571 ,(2002) , 10.1007/3-540-47967-8_37
Aaron F. Bobick, Stephen S. Intille, Large Occlusion Stereo International Journal of Computer Vision. ,vol. 33, pp. 181- 200 ,(1999) , 10.1023/A:1008150329890
S. Roy, I.J. Cox, A maximum-flow formulation of the N-camera stereo correspondence problem international conference on computer vision. pp. 492- 499 ,(1998) , 10.1109/ICCV.1998.710763
Yuichi Ohta, Takeo Kanade, Stereo by Intra- and Inter-Scanline Search Using Dynamic Programming IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-7, pp. 139- 154 ,(1985) , 10.1109/TPAMI.1985.4767639
T. Kanade, 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 ,(1994) , 10.1109/34.310690
Masatoshi Okutomi, Yasuhiro Katayama, Setsuko Oka, A simple stereo algorithm to recover precise object boundaries and smooth surfaces International Journal of Computer Vision. ,vol. 47, pp. 261- 273 ,(2001) , 10.1023/A:1014510328154
Daniel Scharstein, Richard Szeliski, A taxonomy and evaluation of dense two-frame stereo correspondence algorithms International Journal of Computer Vision. ,vol. 47, pp. 7- 42 ,(2001) , 10.1023/A:1014573219977
H. Tao, H.S. Sawhney, R. Kumar, A global matching framework for stereo computation international conference on computer vision. ,vol. 1, pp. 532- 539 ,(2001) , 10.1109/ICCV.2001.937562
C.L. Zitnick, T. Kanade, A cooperative algorithm for stereo matching and occlusion detection IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 22, pp. 675- 684 ,(2000) , 10.1109/34.865184
Minglun Gong, Yee-Hong Yang, Multi-resolution stereo matching using genetic algorithm Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001). pp. 21- 29 ,(2001) , 10.1109/SMBV.2001.988759