No abstract

The existing sparse representation-based visual trackers mostly suffer from both being time consuming and having poor robustness problems. To address these issues, a novel tracking method is presented via combining sparse representation and an emerging learning technique, namely extreme learning machine (ELM). Specifically, visual tracking can be divided into two consecutive processes. Firstly, ELM is utilized to find the optimal separate hyperplane between the target observations and background ones. Thus, the trained ELM classification function is able to remove most of the candidate samples related to background contents efficiently, thereby reducing the total computational cost of the following sparse representation. Secondly, to further combine ELM and sparse representation, the resultant confidence values (i.e., probabilities to be a target) of samples on the ELM classification function are used to construct a new manifold learning constraint term of the sparse representation framework, which tends to achieve robuster results. Moreover, the accelerated proximal gradient method is used for deriving the optimal solution (in matrix form) of the constrained sparse tracking model. Additionally, the matrix form solution allows the candidate samples to be calculated in parallel, thereby leading to a higher efficiency. Experiments demonstrate the effectiveness of the proposed tracker.

A novel object tracking method is proposed that takes advantage of the fast learning capability of extreme learning machine (ELM). Specifically, object tracking is viewed as a binary classification problem, and ELM is utilised for finding the optimal separate hyperplane between the object and backgrounds efficiently. To achieve a more robust tracking, two constraints are introduced in ELM training: (i) target visual changes across frames are smooth (i.e. smoothness) and (ii) probabilities to be true object of image samples around the tracked target trajectory are preferred than those of background ones (i.e. preference). Experiments on challenging sequences demonstrate that the proposed tracker performs favourably against the state-of-the-art methods.

No abstract