Papers › UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation

UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation

14 Dec 2023arXiv:2312.08952archive 2025-07-28

Kefu Yi, Kai Luo, Xiaolei Luo, Jiangui Huang, Hao Wu, Rongdong Hu, Wei Hao

Multi-object tracking (MOT) in video sequences remains a challenging task, especially in scenarios with significant camera movements. This is because targets can drift considerably on the image plane, leading to erroneous tracking outcomes. Addressing such challenges typically requires supplementary appearance cues or Camera Motion Compensation (CMC). While these strategies are effective, they also introduce a considerable computational burden, posing challenges for real-time MOT. In response to this, we introduce UCMCTrack, a novel motion model-based tracker robust to camera movements. Unlike conventional CMC that computes compensation parameters frame-by-frame, UCMCTrack consistently applies the same compensation parameters throughout a video sequence. It employs a Kalman filter on the ground plane and introduces the Mapped Mahalanobis Distance (MMD) as an alternative to the traditional Intersection over Union (IoU) distance measure. By leveraging projected probability distributions on the ground plane, our approach efficiently captures motion patterns and adeptly manages uncertainties introduced by homography projections. Remarkably, UCMCTrack, relying solely on motion cues, achieves state-of-the-art performance across a variety of challenging datasets, including MOT17, MOT20, DanceTrack and KITTI. More details and code are available at https://github.com/corfyi/UCMCTrack

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

corfyi/ucmctrack officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Motion CompensationMulti-Object TrackingMultiple Object TrackingObjectObject Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking DanceTrack UCMCTrack HOTA 63.6 #15 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack UCMCTrack IDF1 65.0 #15 of 37 Archive leaderboard report
Multi-Object Tracking MOT17 UCMCTrack HOTA 65.8 #4 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 UCMCTrack IDF1 81.1 #4 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 UCMCTrack MOTA 80.5 #4 of 48 Archive leaderboard report
Multi-Object Tracking MOT20 UCMCTrack HOTA 62.8 #10 of 27 Archive leaderboard report
Multi-Object Tracking MOT20 UCMCTrack IDF1 77.4 #10 of 27 Archive leaderboard report
Multiple Object Tracking KITTI Test (Online Methods) UCMCTrack HOTA 77.1 #11 of 34 Archive leaderboard report
Multiple Object Tracking KITTI Test (Online Methods) UCMCTrack MOTA 90.4 #11 of 34 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections