Visual tracking via manifold regularized local structured sparse representation model

In this paper, we propose a new visual tracking method via the manifold regularized local structured sparse representation model under the particle filtering tracking framework. First, in order to tackle the difficulties of partial occlusion and illumination variation, the local structured sparse representation model is incorporated by exploiting both partial and spatial information of the target. Second, the manifold regularization is used to ensure that neighboring particles should share similar representation coefficients, so that these particles can cooperate with each other. Extensive experiments are performed on various video sequences, showing improvement over the state-of-the-art approaches.