Online multi-person tracking for intelligent video surveillance systems

This paper presents a novel online multi-person tracking method based on tracking-by-detection framework for intelligent video surveillance systems consisting of an internet protocol (IP) camera and a network video recorder (NVR). First, the two-step data association based on high/low confidence targets is proposed for handling long-term occlusions effectively. Additionally, the method that reasons and handles severe inter-target occlusion is proposed. Representative experimental results demonstrate the effectiveness and robustness of the proposed method.