Multi-Metric Re-Identification for Online Multi-Person Tracking

Multi-person tracking plays a vital role in intelligent video surveillance systems and has attracted researchers' growing attention in recent years. This paper proposes a tracking-by-detection method to detect and track all existing persons in video sequences. The proposed method re-identifies detected persons in the latest video frame as observed persons in previous frames and thus generates their trajectories. Re-identification of the proposed approach uses a fusion of six distance metrics. Four metrics, i.e., position, scale, distance to estimated position, and tracklet continuity, are derived from two motion-based features, and two metrics, i.e., dominant colors and histogram of oriented gradients, are derived from corresponding appearance-based features. The proposed method performs tracking in two general steps per each frame. In the first step, all persons in the video frame are detected using the state-of-the-art YOLOv3 object detector. In the second step, the re-identification algorithm generates correspondences between detected persons in the latest video frame and observed persons in previous frames, using the distance matrix built up from compound distances between all detected-observed person pairs. Experimental results show that our simple yet effective approach achieves significant performance in multi-person tracking compared to existing state-of-the-art methods.