Multi-person multi-camera tracking for live stream videos based on improved motion model and matching cascade

Multiple live videos are streamed to the security room in the video surveillance system of a museum, shopping mall, plaza, etc. For public safety and crowd research, multi-person tracking is essential in these small-scale distributed multi-camera systems. This paper presents a multi-person multi-camera tracking framework for live stream videos. It is compatible with both overlapping and non-overlapping views. Since the tracking framework cannot consistently achieve real-time performance, live stream videos are probably sub-sampled. This sub-sampled issue will enlarge the error of every tracked person's predicted bounding box at each frame. A time-based motion model studying the precise time intervals among sub-sampled frames is proposed. Besides, cameras have different orientations and exposures, resulting in false matches when tracked pedestrians cross the camera boundaries. When a tracked person is out of a camera's view, its motion model will fail, and its tracking identity will probably switch when reentering the same camera. An improved multi-person matching cascade scheme is proposed to solve these problems. It can increase the accuracy of inter-camera person re-identification (Re-ID) by taking advantage of association priorities. Experiments are implemented with the EPFL dataset and live stream videos. Results show that the proposed method has robust performances in different situations. (C) 2021 Published by Elsevier B.V.