We propose an object tracking algorithm that learns a set of appearance models for adaptive discriminative object representation. In this paper, object tracking is posed as a binary classification problem in which the correlation of object appearance and class labels from foreground and background is modeled by partial least squares (PLS) analysis, for generating a low-dimensional discriminative feature subspace. As object appearance is temporally correlated and likely to repeat over time, we learn and adapt multiple appearance models with PLS analysis for robust tracking. The proposed algorithm exploits both the ground truth appearance information of the target labeled in the first frame and the image observations obtained online, thereby alleviating the tracking drift problem caused by model update. Experiments on numerous challenging sequences and comparisons to state-of-the-art methods demonstrate favorable performance of the proposed tracking algorithm.
Bibliographical noteFunding Information:
Manuscript received October 3, 2011; revised March 17, 2012; accepted May 11, 2012. Date of publication June 22, 2012; date of current version September 13, 2012. The work of Q. Wang and F. Chen was supported in part by the Natural Science Foundation of China under Grant 61071131 and the Beijing Natural Science Foundation (NSF) under Grant 4122040. The work of W. Xu was supported in part by the National Key Basic Research and Development Program of China under Grant 2009CB320602. The work of M.-H. Yang was supported in part by the NSF CAREER under Grant 1149783 and NSF IIS under Grant 1152576. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Theo Gevers.
All Science Journal Classification (ASJC) codes
- Computer Graphics and Computer-Aided Design