Resolving motion correspondence for densely moving points Export

@article{citeulike:1877079, abstract = {Studies the motion correspondence problem for which a diversity of qualitative and statistical solutions exist. We concentrate on qualitative modeling, especially in situations where assignment conflicts arise either because multiple features compete for one detected point or because multiple detected points fit a single feature point. We leave out the possibility of point track initiation and termination because that principally conflicts with allowing for temporary point occlusion. We introduce individual, combined, and global motion models and fit existing qualitative solutions in this framework. Additionally, we present a tracking algorithm that satisfies these-possibly constrained-models in a greedy matching sense, including an effective way to handle detection errors and occlusion. The performance evaluation shows that the proposed algorithm outperforms existing greedy matching algorithms. Finally, we describe an extension to the tracker that enables automatic initialization of the point tracks. Several experiments show that the extended algorithm is efficient, hardly sensitive to its few parameters, and qualitatively better than other algorithms, including the presumed optimal statistical multiple hypothesis tracker}, author = {Veenman, C. J. and Reinders, M. J. T. and Backer, E.}, booktitle = {Transactions on Pattern Analysis and Machine Intelligence}, citeulike-article-id = {1877079}, citeulike-linkout-0 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=899946}, journal = {Transactions on Pattern Analysis and Machine Intelligence}, keywords = {correspondence, model, motion, point, tracking}, number = {1}, pages = {54--72}, posted-at = {2007-11-07 10:24:02}, priority = {5}, title = {Resolving motion correspondence for densely moving points}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=899946}, volume = {23}, year = {2001} }

TY - JOUR ID - citeulike:1877079 L3 - citeulike-article-id:1877079 N2 - Studies the motion correspondence problem for which a diversity of qualitative and statistical solutions exist. We concentrate on qualitative modeling, especially in situations where assignment conflicts arise either because multiple features compete for one detected point or because multiple detected points fit a single feature point. We leave out the possibility of point track initiation and termination because that principally conflicts with allowing for temporary point occlusion. We introduce individual, combined, and global motion models and fit existing qualitative solutions in this framework. Additionally, we present a tracking algorithm that satisfies these-possibly constrained-models in a greedy matching sense, including an effective way to handle detection errors and occlusion. The performance evaluation shows that the proposed algorithm outperforms existing greedy matching algorithms. Finally, we describe an extension to the tracker that enables automatic initialization of the point tracks. Several experiments show that the extended algorithm is efficient, hardly sensitive to its few parameters, and qualitatively better than other algorithms, including the presumed optimal statistical multiple hypothesis tracker IS - 1 JF - Transactions on Pattern Analysis and Machine Intelligence EP - 72 TI - Resolving motion correspondence for densely moving points VL - 23 T2 - Transactions on Pattern Analysis and Machine Intelligence SP - 54 KW - correspondence KW - model KW - motion KW - point KW - tracking AU - Veenman, CJ AU - Reinders, MJT AU - Backer, E PY - 2001/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=899946 ER -