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