Sparse Coding and Counting for Robust Visual Tracking

TL;DR

This paper introduces a novel Bayesian sparse coding and counting method for visual tracking that effectively handles occlusion and corruption, achieving real-time performance with improved accuracy.

Contribution

It combines L0 and L1 regularization in a Bayesian framework and develops a fast APG algorithm for real-time robust visual tracking.

Findings

Achieves state-of-the-art accuracy on challenging videos

Operates in real-time with high speed

Effectively handles occlusion and image corruption

Abstract

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.