VariabilityTrack:Multi-Object Tracking with Variable Speed Object Movement

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 can greatly improve the tracking effect in complex variable speed scenes while maintaining high tracking accuracy in relatively static scenes. Eventually, higher MOTA and IDF1 results can be achieved on MOT17 test set than ByteTrack