A novel framework for robust long-term object tracking in real-time

Abstract

In this paper, we study the problem of long-term object tracking, where the object may become fully occluded or leave/re-enter the camera view. In this setting, the drifting due to significant appearance change of the object and the recovery from tracking failure are two major issues. To address these two issues, we propose an intelligent framework to integrate a tracker and detector, wherein the tracker module is used to validate the output of the detector with online learning. The key insight of our work is the importance of how a tracker and detector are integrated, which has received little attention in the literature. Based on our proposed framework, a correlation filter-based tracker and a cascaded detector are utilized to implement a robust long-term tracking algorithm. Extensive experimental results show that the proposed framework performs better compared to specific choices of tracker/detector modules and to state-of-the-art tracking-and-detection methods. Additionally, we extend the proposed system with a centralized strategy to achieve cooperative tracking using multiple cameras in a laboratory setting.