Oct 2026· Conference on Advanced Algorithms and Signal Image Processing· Vol 14370, pp. 143701G - 143701G-8· 0 citations· 15 references
Engineering
TL;DR
Experiments demonstrate that the proposed embedding-motion fusion strategy reduces identity switches and improves AMOTA and IDF1 compared with a JPDA-style motion-only baseline, indicating that learned radar point-cloud correlation can effectively complement interpretable motion cues, leading to more robust association for 4D radar multi-object tracking.
Abstract
Robust multi-object tracking is essential for autonomous driving systems, where accurate perception of dynamic objects directly supports trajectory prediction, obstacle avoidance, and path planning. Compared with cameras and LiDAR, 4D millimeter-wave radar provides all-weather sensing capability and direct Doppler velocity measurements, making it a promising sensor for reliable tracking in challenging environments. However, 4D radar point clouds are typically sparse, noisy, and temporally unstable, which makes identity-consistent association difficult, especially when nearby targets interact or radar reflections fluctuate across frames. To address these challenges, this paper proposes a contrastive Siamese association framework for 4D radar multi-object tracking. Object-level point clouds from historical tracks and current observations are mapped by a full-weight-sharing Siamese encoder into compact dense embeddings, where discriminative point-cloud correlations are learned for track-observation matching. The learned embedding matching probability is further fused with a constant-velocity position likelihood to construct a unified association matrix for online data association. In addition, a hybrid training objective with contrastive warmup and progressive binary cross-entropy mixing is combined with range truncation and static-point filtering to improve training stability, suppress clutter, and enhance score calibration. Experiments on V2X 4D radar data under an oracle-detections protocol demonstrate that the proposed embedding-motion fusion strategy reduces identity switches and improves AMOTA and IDF1 compared with a JPDA-style motion-only baseline. These results indicate that learned radar point-cloud correlation can effectively complement interpretable motion cues, leading to more robust association for 4D radar multi-object tracking.
Experimental results on VoD and TJ4DRadSet demonstrate that the proposed radar-only method achieves competitive performance, even comparable to several radar-camera fusion methods, while maintaining a favorable balance between detection accuracy and inference efficiency.
Multi-Object Tracking (MOT) is essential for EdgeAI perception systems, where accurate object localization and reliable identification enable safe decision-making. Singleagent MOT suffers from occlusions, sensor noise, and partial scene understanding in complex real-world scenarios. While multi-agent systems improve ro...
Maria Damanaki, Nikos Piperigkos, Alexandros Gkillas et al.· arXiv.org· 0 citations
A data-driven state PRedictor-based Interacting Multiple Model tracking method (PR-IMM) that improves nonlinear object-motion representation while preserving the stability and interpretability of physics-based motion models.
This review provides a task-oriented perspective on the transition from sparse object perception to dynamic spatial understanding and summarizes the task coverage, input data, annotations, and evaluation protocols of existing datasets, clarifying the empirical support for different research directions.
Xu-Min Wu, Jun-Lin Zhou, Ji-Lin Mei et al.· 0 citations
With the rapid development of intelligent maritime systems and unmanned surface vehicles (USVs), accurate ship detection and multi-object tracking in complex maritime environments have become essential for autonomous perception and intelligent navigation. However, challenges such as scale variations, background interfe...
Jun-Jie Gao, Liang Hong, Si-Bo Zhang· Italian National Conference...· 0 citations
Multiple object tracking (MOT) from unmanned aerial vehicles (UAVs) presents significant challenges due to drastic viewpoint changes and ambiguous top-down appearances. The former often result in large, misleading displacements of objects in the image plane, while the latter makes it difficult to distinguish between ob...
Ya-Xuan Hu, Jie Hua, Jian-Feng Ding et al.· IEEE Transactions on Geoscie...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.