Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans

@inproceedings{citeulike:2672194, abstract = {Tracking object in low frame rate video or with abrupt motion poses two main difficulties which conventional tracking methods can barely handle: 1) poor motion continuity and increased search space; 2) fast appearance variation of target and more background clutter due to increased search space. In this paper, we address the problem from a view which integrates conventional tracking and detection, and present a temporal probabilistic combination of discriminative observers of different lifespans. Each observer is learned from different ranges of samples, with different subsets of features, to achieve varying level of discriminative power at varying cost. An efficient fusion and temporal inference is then done by a cascade particle filter which consists of multiple stages of importance sampling. Experiments show significantly improved accuracy of the proposed approach in comparison with existing tracking methods, under the condition of low frame rate data and abrupt motion of both target and camera.}, author = {Li, Yuan and Ai, Haizhou and Yamashita, T. and Lao, Shihong and Kawade, M. }, booktitle = {Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on}, citeulike-article-id = {2672194}, doi = {10.1109/CVPR.2007.383199}, journal = {Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on}, pages = {1--8}, posted-at = {2008-04-15 08:57:40}, priority = {2}, title = {Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans}, url = {http://dx.doi.org/10.1109/CVPR.2007.383199}, year = {2007} }

TY - CONF ID - citeulike:2672194 L3 - citeulike-article-id:2672194 TI - Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans T2 - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on JF - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on SP - 1 EP - 8 N2 - Tracking object in low frame rate video or with abrupt motion poses two main difficulties which conventional tracking methods can barely handle: 1) poor motion continuity and increased search space; 2) fast appearance variation of target and more background clutter due to increased search space. In this paper, we address the problem from a view which integrates conventional tracking and detection, and present a temporal probabilistic combination of discriminative observers of different lifespans. Each observer is learned from different ranges of samples, with different subsets of features, to achieve varying level of discriminative power at varying cost. An efficient fusion and temporal inference is then done by a cascade particle filter which consists of multiple stages of importance sampling. Experiments show significantly improved accuracy of the proposed approach in comparison with existing tracking methods, under the condition of low frame rate data and abrupt motion of both target and camera. AU - Li, Yuan AU - Ai, Haizhou AU - Yamashita, T AU - Lao, Shihong AU - Kawade, M PY - 2007/// UR - http://dx.doi.org/10.1109/CVPR.2007.383199 ER -