VariabilityTrack:Multi-Object Tracking with Variable Speed Object Movement
Run Luo, JinLin Wei, and Qiao Lin

TL;DR
This paper introduces a variable speed Kalman filter for multi-object tracking that adapts to environmental feedback, significantly improving tracking accuracy in complex scenes with variable object speeds while maintaining high performance in static scenes.
Contribution
It proposes a novel variable speed Kalman filter and an improved matching process to enhance multi-object tracking in dynamic environments, outperforming existing methods like ByteTrack.
Findings
Achieves higher MOTA and IDF1 scores on MOT17 test set.
Improves tracking performance in scenes with vehicle and UAV acceleration.
Maintains high accuracy in static scenes.
Abstract
Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods can be roughly classified as tracking-by-detection and joint-detection-association paradigms. Although the latter has elicited more attention and demonstrates comparable performance relative than the former, we claim that the tracking-by-detection paradigm is still the optimal solution in terms of tracking accuracy,such as ByteTrack,which achieves 80.3 MOTA, 77.3 IDF1 and 63.1 HOTA on the test set of MOT17 with 30 FPS running speed on a single V100 GPU.However, under complex perspectives such as vehicle and UAV acceleration, the performance of such a tracker using uniform Kalman filter will be greatly affected, resulting in tracking loss.In this paper, we propose a variable speed Kalman filter algorithm based on environmental feedback and improve the matching process, which…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVideo Surveillance and Tracking Methods · Target Tracking and Data Fusion in Sensor Networks · UAV Applications and Optimization
MethodsSPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings
