Pattern Recognition, International Conference on (2010)
Aug. 23, 2010 to Aug. 26, 2010
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICPR.2010.641
This paper addresses the problem of object tracking by learning a discriminative classifier to separate the object from its background. The online-learned classifier is used to adaptively model object's appearance and its background. To solve the typical problem of erroneous training examples generated during tracking, an online multiple instance learning (MIL) algorithm is used by allowing false positive examples. In addition, particle filter is applied to make best use of the learned classifier and help to generate a better representative set of training examples for the online MIL learning. The effectiveness of the proposed algorithm is demonstrated in some challenging environments for human tracking.
particle filter tracking, multiple instance learning
Z. Ni, A. Rahimi, S. Sunderrajan and B. Manjunath, "Particle Filter Tracking with Online Multiple Instance Learning," 2010 20th International Conference on Pattern Recognition (ICPR 2010)(ICPR), Istanbul, 2010, pp. 2616-2619.