Sparse feature representation for visual tracking

Abstract

In this paper, a novel sparse feature representation method for object tracking is proposed. The method is on the observation that a tracked object can be dynamically and compactly represented by a few features (sparse representation) from a large feature set (the improved histogram of oriented gradient and color, HOGC). Based on the HOGC features, the sparse representation can be learned online from the constructed training samples during the tracking procedure by exploiting the L1-norm minimization principle, which can also be called feature selection procedure, ensuring the tracking can adapt to the appearance variations of either foreground or background. Experiments with comparisons demonstrate the effectiveness of the proposed method.