Robust Visual Tracking Using Latent Subspace Projection Pursuit

With the development of computer vision, object tracking has attracted more and more attention in some research fields such as motion analysis, activity recognition and medical image. Even though various algorithms have come out, it is still a challenge problem due to complex object motion, heavy occlusion, illumination change and background clutter.Benefiting from the great success of Particle Filtering, object tracking has been transformed into a Bayesian inference. problem in state space.In this paper, a novel subspace learning algorithm is proposed for robust visual tracking. Different from conventional subspace 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.