Patch-based robust L1 tracker to dynamic appearance change
Won Jin Kim, Tae-Hyun Oh, Kyungdon Joo, In So Kweon · 2013
In this paper, we propose a robust l1tracking method based on a two phases sparse representation, which consists of a patch and a global appearance trackers. While recently proposed l1trackers showed impressive tracking accuracies, tracking the dynamic appearance is not easy to them. To overcome dynamic appearance change and achieve robust visual tracking, we model the dynamic appearance of the object by a set of local rigid patches and enhance the distinctiveness of the global appearance tracker by positive/negative learning. The integration of two approaches makes visual tracking robust to occlusion and illumination variation. We demonstrate the experiments with five challenging video sequences and compare with state-of-art trackers. We show that the proposed method successfully handle occlusion, noise, scale, illumination, and appearance change of the object.