Saved in:
Bibliographic Details
Main Authors: Gong, Yan, Chen, Mengjun, Liu, Hao, Yongsheng, Gao, Yang, Lei, Wang, Naibang, Song, Ziying, Ma, Haoqun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.00358
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909715911409664
author Gong, Yan
Chen, Mengjun
Liu, Hao
Yongsheng, Gao
Yang, Lei
Wang, Naibang
Song, Ziying
Ma, Haoqun
author_facet Gong, Yan
Chen, Mengjun
Liu, Hao
Yongsheng, Gao
Yang, Lei
Wang, Naibang
Song, Ziying
Ma, Haoqun
contents Multi-object tracking (MOT) enables autonomous vehicles to continuously perceive dynamic objects, supplying essential temporal cues for prediction, behavior understanding, and safe planning. However, conventional tracking-by-detection methods typically rely on static coordinate transformations based on ego-vehicle poses, disregarding ego-vehicle speed-induced variations in observation noise and reference frame changes, which degrades tracking stability and accuracy in dynamic, high-speed scenarios. In this paper, we investigate the critical role of ego-vehicle speed in MOT and propose a Speed-Guided Learnable Kalman Filter (SG-LKF) that dynamically adapts uncertainty modeling to ego-vehicle speed, significantly improving stability and accuracy in highly dynamic scenarios. Central to SG-LKF is MotionScaleNet (MSNet), a decoupled token-mixing and channel-mixing MLP that adaptively predicts key parameters of SG-LKF. To enhance inter-frame association and trajectory continuity, we introduce a self-supervised trajectory consistency loss jointly optimized with semantic and positional constraints. Extensive experiments show that SG-LKF ranks first among all vision-based methods on KITTI 2D MOT with 79.59% HOTA, delivers strong results on KITTI 3D MOT with 82.03% HOTA, and outperforms SimpleTrack by 2.2% AMOTA on nuScenes 3D MOT.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00358
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stable at Any Speed: Speed-Driven Multi-Object Tracking with Learnable Kalman Filtering
Gong, Yan
Chen, Mengjun
Liu, Hao
Yongsheng, Gao
Yang, Lei
Wang, Naibang
Song, Ziying
Ma, Haoqun
Computer Vision and Pattern Recognition
Multi-object tracking (MOT) enables autonomous vehicles to continuously perceive dynamic objects, supplying essential temporal cues for prediction, behavior understanding, and safe planning. However, conventional tracking-by-detection methods typically rely on static coordinate transformations based on ego-vehicle poses, disregarding ego-vehicle speed-induced variations in observation noise and reference frame changes, which degrades tracking stability and accuracy in dynamic, high-speed scenarios. In this paper, we investigate the critical role of ego-vehicle speed in MOT and propose a Speed-Guided Learnable Kalman Filter (SG-LKF) that dynamically adapts uncertainty modeling to ego-vehicle speed, significantly improving stability and accuracy in highly dynamic scenarios. Central to SG-LKF is MotionScaleNet (MSNet), a decoupled token-mixing and channel-mixing MLP that adaptively predicts key parameters of SG-LKF. To enhance inter-frame association and trajectory continuity, we introduce a self-supervised trajectory consistency loss jointly optimized with semantic and positional constraints. Extensive experiments show that SG-LKF ranks first among all vision-based methods on KITTI 2D MOT with 79.59% HOTA, delivers strong results on KITTI 3D MOT with 82.03% HOTA, and outperforms SimpleTrack by 2.2% AMOTA on nuScenes 3D MOT.
title Stable at Any Speed: Speed-Driven Multi-Object Tracking with Learnable Kalman Filtering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.00358