Sparse Coding and Counting for Robust Visual Tracking

• DOI: 10.1371/journal.pone.0168093
• Publication Date: 2016-12-19T18:41:48Z
• Authors: Risheng Liu; Jing Wang; Xiaoke Shang; Yiyang Wang; Zhixun Su; Yu Cai
• Keywords: Neural coding; Representation

In this paper, we propose a novel sparse coding and counting method under Bayesian framework for visual tracking. contrast to existing methods, the proposed employs combination of L0 L1 norm regularize linear coefficients incrementally updated basis. The sparsity constraint enables tracker effectively handle difficult challenges, such as occlusion or image corruption. To achieve real-time processing, fast efficient numerical algorithm solving model. Although it is an NP-hard problem, accelerated proximal gradient (APG) approach guaranteed converge solution quickly. Besides, provide closed combining regularized representation obtain better sparsity. Experimental results on challenging video sequences demonstrate that achieves state-of-the-art both in accuracy speed.