Simultaneous motion-disparity estimation and segmentation from stereo
作者： Y. Altunbasak , A.M. Tekalp , G. Bozdagi
关键词:
摘要: Both motion/structure estimation from monocular video and disparity still-frame stereo are known to be ill-posed problems. Further, because varies by depth, motion parameters different for independently moving objects, they can both benefit scene segmentation. To this effect, we present a framework simultaneous including segmentation in video. In formulation, pairs of parameter vector values segmented into K regions, where within each region single set is defined, the field allowed vary smoothly. The algorithm iterates between computing maximum posteriori probability (MAP) estimates fields conditioned on estimates, likelihood (hit) via simulated annealing (SA). Simulation results provided. >
sci-hub.se 参考文章(11)
Christoph Stiller, Bernd Huertgen, Combined displacement estimation and segmentation in image sequences Video Communications and PACS for Medical Applications. ,vol. 1977, pp. 276- 287 ,(1993) , 10.1117/12.160473
Michael Hötter, Robert Thoma, Image segmentation based on object oriented mapping parameter estimation Signal Processing. ,vol. 15, pp. 315- 334 ,(1988) , 10.1016/0165-1684(88)90021-7
David W. Murray, Bernard F. Buxton, Scene Segmentation from Visual Motion Using Global Optimization IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-9, pp. 220- 228 ,(1987) , 10.1109/TPAMI.1987.4767896
Zhengyou Zhang, Olivier D Faugeras, None, Three-dimensional motion computation and object segmentation in a long sequence of stereo frames International Journal of Computer Vision. ,vol. 7, pp. 211- 241 ,(1992) , 10.1007/BF00126394
Gilad Adiv, Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-7, pp. 384- 401 ,(1985) , 10.1109/TPAMI.1985.4767678
U.R. Dhond, J.K. Aggarwal, Structure from stereo-a review systems man and cybernetics. ,vol. 19, pp. 1489- 1510 ,(1989) , 10.1109/21.44067
Allen M. Waxman, James H. Duncan, Binocular Image Flows: Steps Toward Stereo-Motion Fusion IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-8, pp. 715- 729 ,(1986) , 10.1109/TPAMI.1986.4767853
Z. Kato, M. Berthod, J. Zerubia, Parallel image classification using multiscale Markov random fields IEEE International Conference on Acoustics Speech and Signal Processing. ,vol. 5, pp. 137- 140 ,(1993) , 10.1109/ICASSP.1993.319766
T.S. Huang, A.N. Netravali, Motion and structure from feature correspondences: a review Proceedings of the IEEE. ,vol. 82, pp. 252- 268 ,(1994) , 10.1109/5.265351
M.M. Chang, M.I. Sezan, A.M. Tekalp, An algorithm for simultaneous motion estimation and scene segmentation international conference on acoustics, speech, and signal processing. pp. 221- 224 ,(1994) , 10.1109/ICASSP.1994.389492