A non-iterative greedy algorithm for multi-frame point correspondence Export

@inproceedings{citeulike:1943020, abstract = {We present a framework for finding point correspondences in monocular image sequences over multiple frames. The general problem of multiframe point correspondence is NP hard for three or more frames. A polynomial time algorithm for a restriction of this problem is presented, and is used as the basis of proposed greedy algorithm for the general problem. The greedy nature of the proposed algorithm allows it to be used in real time systems for tracking and surveillance etc. In addition, the proposed algorithm deals with the problems of occlusion, missed detections, and false positives, by using a single noniterative greedy optimization scheme, and hence, reduces the complexity of the overall algorithm as compared to most existing approaches, where multiple heuristics are used for the same purpose. While most greedy algorithms for point tracking do not allow for entry and exit of points from the scene, this is not a limitation for the proposed algorithm. Experiments with real and synthetic data show that the proposed algorithm outperforms the existing techniques and is applicable in more general settings.}, author = {Shafique, K. and Shah, M.}, booktitle = {Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on}, citeulike-article-id = {1943020}, citeulike-linkout-0 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1238321}, journal = {Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on}, keywords = {correspondence, deterministic, greedy, point, tracking}, pages = {110--115 vol.1}, posted-at = {2007-11-20 11:32:54}, priority = {5}, title = {A non-iterative greedy algorithm for multi-frame point correspondence}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1238321}, year = {2003} }

TY - CONF ID - citeulike:1943020 L3 - citeulike-article-id:1943020 N2 - We present a framework for finding point correspondences in monocular image sequences over multiple frames. The general problem of multiframe point correspondence is NP hard for three or more frames. A polynomial time algorithm for a restriction of this problem is presented, and is used as the basis of proposed greedy algorithm for the general problem. The greedy nature of the proposed algorithm allows it to be used in real time systems for tracking and surveillance etc. In addition, the proposed algorithm deals with the problems of occlusion, missed detections, and false positives, by using a single noniterative greedy optimization scheme, and hence, reduces the complexity of the overall algorithm as compared to most existing approaches, where multiple heuristics are used for the same purpose. While most greedy algorithms for point tracking do not allow for entry and exit of points from the scene, this is not a limitation for the proposed algorithm. Experiments with real and synthetic data show that the proposed algorithm outperforms the existing techniques and is applicable in more general settings. JF - Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on EP - 115 vol.1 TI - A non-iterative greedy algorithm for multi-frame point correspondence T2 - Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on SP - 110 KW - correspondence KW - deterministic KW - greedy KW - point KW - tracking AU - Shafique, K AU - Shah, M PY - 2003/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1238321 ER -