Discriminative descriptors for object tracking

Abstract

Object tracking is one of the most challenging problems in computer vision. Only Fast trackers can satisfy the real-time requirements and can be used in many artificial intelligence applications. Due to the impressive high-speed, correlation filters have received much attention within the field of object tracking. Recently, trackers using luminance information or color names for image description have been performed in a correlation filters framework. In this paper, we propose the usage of discriminative color descriptors to improve the tracking performance of the traditional correlation filters tracker. Discriminative color descriptors are compact and efficient. Moreover, our tracker incorporates scale estimation into the traditional correlation filters, which results in increased tracking performance. Extensive experiments demonstrate that the proposed tracker can obtain superior results compared to existing trackers using correlation filters and it is also able to outperform state-of-the-art trackers on the CVPR2013 object tracking benchmark.