Effective object tracking using extreme learning machine with smoothness and preference regularisation

Abstract

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.