Correlation filter tracker with siamese: A robust and real-time object tracking framework

Abstract

Correlation filter (CF) based trackers have shown promising performance in object tracking. However, both the accuracy and efficiency of existing CF based trackers are limited. In this paper, we propose a robust and real-time object tracking framework, based on a canonical CF tracker. Specifically, we first propose an adaptive model update strategy for preventing the tracker from being contaminated when the target is occluded or disappears in sight. Then, we propose a multimodal validation method for reducing tracking failures, which is capable of generating potential candidates adaptively and evaluating them with a siamese network. In addition, we build a template library online to augment the discriminability of the employed siamese network. Experimental results over OTB-13 and OTB-15 benchmark datasets demonstrate that our method outperforms state-of-the-art ones. Especially, on OTB-15, our method not only achieves a relative gain of 12.3% in AUC score but also runs at a high tracking speed, i.e., 58.3 frames per second, in comparison with the baseline CF tracker.