Adaptive Multi-Level 3D Multi-Object Tracking with Transformer-Based Association and Scene-Aware Thresholds for Autonomous Driving
Machines · 23.04.2026 · 14 (5) · 472
DOI: 10.3390/machines14050472 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machines, online erschienen am 23.04.2026. Verfasst von Yongze Zhang und 2 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Jiangsu province frontier leading technology basic research project.
Abstract (Originalsprache)
3D multi-object tracking (MOT) for autonomous driving remains challenging due to frequent identity switches in crowded scenes, trajectory fragmentation during occlusions, and the difficulty of adapting association strategies to varying scene complexities. While existing methods rely on fixed geometric or appearance-based associations, they struggle to handle ambiguous cases and detection failures. We present an adaptive multi-level 3D MOT framework that achieves robust tracking through three key innovations: (1) multi-granularity temporal modeling that captures both fine-grained short-term motion and coarse long-term trends via dual-scale spatio-temporal attention, enabling accurate motion prediction across different object dynamics; (2) Transformer-based Appearance Association that employs cross-attention to model global inter-object relationships, resolving ambiguous associations in crowded scenarios where geometric cues alone fail; and (3) scene-adaptive learned thresholds that automatically adjust association strictness based on object density, motion complexity, and occlusion levels, avoiding the one-size-fits-all limitations of fixed thresholds. Our hierarchical four-level tracking strategy progressively handles cases from easy geometric matching (Level 1) to complex interval-frame recovery (Level 4), with SOT-based virtual detection generation bridging detector failures. Extensive experiments on the nuScenes benchmark demonstrate state-of-the-art performance.
Förderung
- National Natural Science Foundation of China
- Jiangsu province frontier leading technology basic research project
Zitieren
APA
Zhang, Y., Da, F., & Zhou, H. (2026). Adaptive Multi-Level 3D Multi-Object Tracking with Transformer-Based Association and Scene-Aware Thresholds for Autonomous Driving. Machines, 14(5), 472. https://doi.org/10.3390/machines14050472
Vancouver
Zhang Y, Da F, Zhou H. Adaptive Multi-Level 3D Multi-Object Tracking with Transformer-Based Association and Scene-Aware Thresholds for Autonomous Driving. Machines. 2026;14(5):472. doi:10.3390/machines14050472
BibTeX
@article{Zhang2026,
author = {Zhang, Yongze and Da, Feipeng and Zhou, Haocheng},
title = {Adaptive Multi-Level 3D Multi-Object Tracking with Transformer-Based Association and Scene-Aware Thresholds for Autonomous Driving},
journal = {Machines},
year = {2026},
volume = {14},
number = {5},
pages = {472},
doi = {10.3390/machines14050472}
}
EUVIMED