Abstract

The sparse representation has been widely used in many ar- eas and utilized for visual tracking. Tracking with sparse representation is formulated as searching for samples with minimal reconstruction errors from learned template subspace. However, the computational cost makes it unsuitable to utilize high dimensional advanced features which are of- ten important for robust tracking under dynamic environment. Based on the observations that a target can be reconstructed from several tem- plates, and only some of the features with discriminative power are sig- nificant to separate the target from the background, we propose a novel online tracking algorithm with two stage sparse optimization to jointly minimize the target reconstruction error and maximize the discrimina- tive power. As the target template and discriminative features usually have temporal and spatial relationship, dynamic group sparsity (DGS) is utilized in our algorithm. The proposed method is compared with three state-of-art trackers using five public challenging sequences, which ex- hibit appearance changes, heavy occlusions, and pose variations. Our algorithm is shown to outperform these methods.