Past Information Aggregation for Multi-Person Tracking

Multi-person tracking is often solved with the tracking-bydetection (TBD) paradigm. So-far tracked targets are matched to new detections on the basis of the current track states including motion or appearance information. If tracks are updated with inaccurate detections or unreliable appearance features, e.g., due to occlusion, the track states can become distorted leading to errors in the association. To mitigate this problem, we propose a simple and generic method for Past Information Aggregation (PIA) that utilizes more tracking information from the past in the association and can be applied within any TBD approach. We combine PIA with a new sophisticated distance measure fusing motion and appearance cues and a second matching stage which further improves the association accuracy. Our tracking framework is analyzed with extensive ablative experiments and state-of-the-art results are achieved on the MOT17 and MOT20 benchmarks.