Robust Real-Time Object Tracking using Tiered Templates
Feng Su, Gu Fang, Ju Jia Zou · 2018
Object tracking has been an important topic in the field of computer vision. This paper proposes a robust method of tracking a moving object continuously in real-time without prior information and learning. The key strategies involved in this novel method are: combining intensity template matching with colour histogram model to increase tracking robustness, employing a three-tier system to store templates, applying update and tracking policies for template management. Experiment results have shown that the proposed method achieved the highest tracking accuracy among existing methods from various benchmark videos.