Large Scale Real-World Multi-Person Tracking

This paper presents a new large scale multi-person tracking dataset -- \texttt{PersonPath22}, which is over an order of magnitude larger than currently available high quality multi-object tracking datasets such as MOT17, HiEve, and MOT20 datasets. The lack of large scale training and test data for this task has limited the community's ability to understand the performance of their tracking systems on a wide range of scenarios and conditions such as variations in person density, actions being performed, weather, and time of day. \texttt{PersonPath22} dataset was specifically sourced to provide a wide variety of these conditions and our annotations include rich meta-data such that the performance of a tracker can be evaluated along these different dimensions. The lack of training data has also limited the ability to perform end-to-end training of tracking systems. As such, the highest performing tracking systems all rely on strong detectors trained on external image datasets. We hope that the release of this dataset will enable new lines of research that take advantage of large scale video based training data.

PDF Abstract ECCV 2022 PDF

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Multi-Object Tracking PersonPath22 ByteTrack IDF1 66.8 # 1
MOTA 75.4 # 1
Multi-Object Tracking PersonPath22 CenterTrack IDF1 46.36 # 4
MOTA 59.28 # 4
Multi-Object Tracking PersonPath22 SiamMOT IDF1 53.71 # 3
MOTA 67.52 # 2
Multi-Object Tracking PersonPath22 FairMOT IDF1 61.05 # 2
MOTA 61.79 # 3

Methods