An equalised global graphical model-based approach for multi-camera object tracking
This addresses the need for effective inter-camera tracking in real surveillance systems, though it appears incremental as it builds on existing multi-camera tracking frameworks.
The paper tackled the problem of multi-camera object tracking in non-overlapping surveillance scenes by proposing a global graph model with an improved similarity metric, which improved overall tracking performance even under poor single-camera tracking conditions.
Non-overlapping multi-camera visual object tracking typically consists of two steps: single camera object tracking and inter-camera object tracking. Most of tracking methods focus on single camera object tracking, which happens in the same scene, while for real surveillance scenes, inter-camera object tracking is needed and single camera tracking methods can not work effectively. In this paper, we try to improve the overall multi-camera object tracking performance by a global graph model with an improved similarity metric. Our method treats the similarities of single camera tracking and inter-camera tracking differently and obtains the optimization in a global graph model. The results show that our method can work better even in the condition of poor single camera object tracking.