Online visual tracking based on subspace representation with continuous occlusion modeling

Abstract

As an important issue in image processing and computer vision, online visual tracking acts a critical role in numerous lines of research and has many potential applications. This paper presents a novel tracking algorithm based on subspace representation with continuous occlusion handling, the contributions of which are threefolds. First, this paper develops an effective objective function to represent the tracked object, in which the object reconstruction, the sparsity of the error term and the spatial consistency of the error term are simultaneously considered. Then, we derive an iterative algorithm to solve the proposed objective function based on the accelerated proximal gradient framework, and therefore obtain the optimal representation coefficients and the possible occlusion conditions. Finally, based on the proposed representation model, we design an effective likelihood function and a simple model update scheme for building a robust tracker within the particle filter framework. We conduct many experiments to evaluate the proposed tracking algorithm in comparisons with other state-of-the-art trackers. Both qualitative and quantitative evaluations demonstrate the proposed tracker achieves good performance.