Real-time Object Tracking via Online Discriminative Feature Selection
Kaihua Zhang1, Lei Zhang1, Ming-Hsuan Yang2
1Depart. of Computing, The Hong Kong Polytechnic University, Hong Kong
2Electrical Engineering and Computer Science, University of California at Merced,
Abstract！Most tracking-by-detection algorithms train discriminative classifiers to separate target objects from their surrounding background. In this setting, noisy samples are likely to be included when they are not properly sampled, thereby causing visual drift. The multiple instance learning (MIL) learning paradigm has been recently applied to alleviate this problem. However, important prior information of instance labels and the most correct positive instance (i.e., the tracking result in the current frame) can be exploited using a novel formulation much simpler than an MIL approach. In this paper, we show that integrating such prior information into a supervised learning algorithm can handle visual drift more effectively and efficiently than the existing MIL tracker. We present an online discriminative feature selection algorithm which optimizes the objective function in the steepest ascent direction with respect to the positive samples while in the steepest descent direction with respect to the negative ones. Therefore, the trained classifier directly couples its score with the importance of samples, leading to a more robust and efficient tracker. Numerous experimental evaluations with state-of-the-art algorithms on challenging sequences demonstrate the merits of the proposed algorithm.
Real-time Object Tracking via Online Discriminative Feature Selection, Kaihua Zhang, Lei Zhang, Ming-Hsuan Yang, submitted.
Supplementary videos for 9 different trackers
Supplementary videos for our tracker and MILTracker with different online update of model parameters
Last updated by Kaihua Zhang on 8/8/2012.