Radar-Informed 3D Multi-Object Tracking under Adverse Conditions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Bingxue, Hedemalm, Emil, Khoche, Ajinkya, Jensfelt, Patric
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908982111633408
author Xu, Bingxue
Hedemalm, Emil
Khoche, Ajinkya
Jensfelt, Patric
author_facet Xu, Bingxue
Hedemalm, Emil
Khoche, Ajinkya
Jensfelt, Patric
contents The challenge of 3D multi-object tracking is achieving robustness in real-world applications, for example under adverse conditions and maintaining consistency as distance increases. To overcome these challenges, sensor fusion approaches that combine LiDAR, cameras, and radar have emerged. However, existing multimodal methods usually treat radar as another learned feature inside the network. When the overall model degrades in difficult environments, the robustness advantages that radar could provide are also reduced. In this paper we propose RadarMOT, a radar-informed 3D multi-object tracking framework that explicitly uses radar point clouds as additional observations to refine state estimation and recover objects missed by the detector at long ranges. Evaluations on the MAN-TruckScenes dataset show that RadarMOT consistently improves the Average Multi-Object Tracking Accuracy (AMOTA) by 12.7\% at long range and up to 10.3\% in adverse weather. The code will be available at https://github.com/bingxue-xu/radarmot
format Preprint
id arxiv_https___arxiv_org_abs_2604_13571
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Radar-Informed 3D Multi-Object Tracking under Adverse Conditions
Xu, Bingxue
Hedemalm, Emil
Khoche, Ajinkya
Jensfelt, Patric
Computer Vision and Pattern Recognition
The challenge of 3D multi-object tracking is achieving robustness in real-world applications, for example under adverse conditions and maintaining consistency as distance increases. To overcome these challenges, sensor fusion approaches that combine LiDAR, cameras, and radar have emerged. However, existing multimodal methods usually treat radar as another learned feature inside the network. When the overall model degrades in difficult environments, the robustness advantages that radar could provide are also reduced. In this paper we propose RadarMOT, a radar-informed 3D multi-object tracking framework that explicitly uses radar point clouds as additional observations to refine state estimation and recover objects missed by the detector at long ranges. Evaluations on the MAN-TruckScenes dataset show that RadarMOT consistently improves the Average Multi-Object Tracking Accuracy (AMOTA) by 12.7\% at long range and up to 10.3\% in adverse weather. The code will be available at https://github.com/bingxue-xu/radarmot
title Radar-Informed 3D Multi-Object Tracking under Adverse Conditions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.13571