The Community for Technology Leaders
Green Image
Issue No. 10 - October (2008 vol. 30)
ISSN: 0162-8828
pp: 1728-1740
Yuan Li , University of Southern California, Los Angeles
Haizhou Ai , Tsinghua University, Beijing
Takayoshi Yamashita , OMRON Corporation, Kyoto
Shihong Lao , OMRON Corporation, Kyoto
Masato Kawade , OMRON Corporation, Kyoto
Tracking object in low frame rate video or with abrupt motion poses two main difficulties which most conventional tracking methods can hardly 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.
Vision and Scene Understanding, Motion

H. Ai, T. Yamashita, S. Lao, Y. Li and M. Kawade, "Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Life Spans," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 30, no. , pp. 1728-1740, 2008.
99 ms
(Ver 3.3 (11022016))