Robust online object tracking via the convex hull representation model

As an important issue in computer vision, online object tracking plays a critical role in numerous lines of research and has many potential applications. This paper presents a novel tracking algorithm based on the convex hull representation model with sparse representation. The tracked object is assumed to be within the object convex hull and the candidate convex hull in the meanwhile. The object convex hull consists of a principle component analysis (PCA) subspace, and the candidate convex hull is constructed by all candidate samples with the sparsity constraint. Then we propose the objective function for our convex hull representation model, and design an iterative algorithm to solve it effectively. Finally, we present a tracking framework based on the proposed convex hull model and a simple online update scheme. Both qualitative and quantitative evaluations on many challenging video clips demonstrate that our tracker achieves better performance than other state-of-the-art methods.