EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RVFNet: 4D mmWave Radar-Vision Fusion Multi-Task Panoptic Perception Network for Unmanned Surface Vehicles

Fangxiang Tang iD, Bing Tang iD, Shenbo Liu iD, Dongxue Zhao iD, Lijun Tang iD, Junlong Tang iD

Sensors · 03.11.2026 · 26 (21) · 6953

DOI: 10.3390/s26216953 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 03.11.2026. Verfasst von Fangxiang Tang und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Physics and Electronic Science, Changsha University of Science and Technology, Changsha 410114, China. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Water Resources Science and Technology Program of Hunan Province, the Basic Research Project for Young Students of the Natural Science Foundation of Hunan Province, China, Basic Research Project for Young Students of the Natural Science Foundation of Hunan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

4D mmWave radar-vision fusion is a low-cost and promising solution for Unmanned Surface Vehicles navigation. However, existing methods mainly focus on single tasks and suffer from insufficient radar feature extraction and inefficient multi-modal fusion. This paper proposes RVFNet, a 4D mmWave radar-visual fusion multi-task perception network. It designs the Radar Feature Enhancement Module (RFEM) and alternately stacks RFEM with conventional convolution blocks to construct the Radar Feature Extraction Network (RFENet), which solves the problem of insufficient extraction of sparse and irregular radar point cloud features and suppresses water-surface clutter; it constructs the Multi-modal Feature Adaptive Fusion Module (MFAFM) with content-guided attention. MFAFM generates dynamic modal weights and adaptively balances visual and radar information to alleviate missed detection and false detection in harsh scenarios. Compared with mainstream methods, experimental results on the WaterScenes dataset show that RVFNet requires only 3.3 GFLOPs while achieving an mAP50 of 79.0%, an mAP50–95 of 46.7%, an mIoU of 84.0% for object segmentation, and an mIoU of 98.8% for drivable-area segmentation, demonstrating superior overall perception performance. Cross-scenario experiments on the FloW-RI water-surface dataset and the nuScenes v1.0-trainval autonomous-driving dataset further verify the strong generalization capability of RVFNet, demonstrating its potential for deployment on embedded devices.

Schlagwörter

Stichwörter der Autor:innen

4D mmWave radarUnmanned Surface Vehiclesmulti-task perceptionradar-vision fusion

Autor:innen und Institutionen

  • School of Physics and Electronic Science, Changsha University of Science and Technology, Changsha 410114, China.
  • Hunan Province Higher Education Key Laboratory of Modeling and Monitoring on the Near-Earth Electromagnetic Environment, Changsha 410114, China.
  • Hunan Provincial Key Laboratory of Flexible Electronic Materials Genome Engineering, Changsha University of Science and Technology, Changsha 410114, China.

ORCID-Profile: Fangxiang Tang, Bing Tang, Shenbo Liu, Dongxue Zhao, Lijun Tang, Junlong Tang

Förderung

  • Water Resources Science and Technology Program of Hunan Province
  • the Basic Research Project for Young Students of the Natural Science Foundation of Hunan Province, China
  • Basic Research Project for Young Students of the Natural Science Foundation of Hunan Province

Zitieren

APA

Tang, F., Tang, B., Liu, S., Zhao, D., Tang, L., & Tang, J. (2026). RVFNet: 4D mmWave Radar-Vision Fusion Multi-Task Panoptic Perception Network for Unmanned Surface Vehicles. Sensors, 26(21), 6953. https://doi.org/10.3390/s26216953

Vancouver

Tang F, Tang B, Liu S, Zhao D, Tang L, Tang J. RVFNet: 4D mmWave Radar-Vision Fusion Multi-Task Panoptic Perception Network for Unmanned Surface Vehicles. Sensors. 2026;26(21):6953. doi:10.3390/s26216953

BibTeX
@article{Tang2026,
  author = {Tang, Fangxiang and Tang, Bing and Liu, Shenbo and Zhao, Dongxue and Tang, Lijun and Tang, Junlong},
  title = {RVFNet: 4D mmWave Radar-Vision Fusion Multi-Task Panoptic Perception Network for Unmanned Surface Vehicles},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {6953},
  doi = {10.3390/s26216953}
}
Kostenlos starten →