Robust visual tracking using latent subspace projection pursuit

In this paper, a novel subspace learning algorithm is proposed for robust visual tracking. Different from conventional sub-space based trackers, which first estimate the dimension of the subspace and then pursuit its basis to construct the subspace projection in appearance model, our method directly learns a low-rank projection with known ranks as subspace dimension to model the subspace structure for visual tracking. Under particle filter tracking framework, an online scheme is developed to incrementally pursue the optimum projection and the candidate with the minimal reconstruction error is selected to deliver the tracking information to the next frame and pursue the projection. The columns of the projection defined in the latent feature space are a set of redundant basis, treating an observation as its coefficient. As a result, the low-rank property of the pursued optimum projection can exactly reveal the intrinsic low-dimensional structure of the global feature space, contributing to the high precision of capturing appearance changes. Experiments on several challenging image sequences demonstrate that our tracker performs excellently against several state-of-the-art trackers.