EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MVDFusion: Multimodal Vehicle Detection in Foggy Weather Using LiDAR and Radar Fusion

Jiake Tian iD, Yan Gao iD, Xin Xia, Guoliang Ju, Peijun Ye, Sijie Tang, Hong Wang, Xucong Wang

Sensors · 25.04.2026 · 26 (9) · 2663

DOI: 10.3390/s26092663 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.04.2026. Verfasst von Jiake Tian und 7 weiteren Autor:innen. Beteiligte Einrichtung: Pengcheng Laboratory, Shenzhen 518055, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Open Research Project of the CMA Key Laboratory of Hydro-Meteorology Project, Science and Technology Project of the Guangdong Meteorological Bureau Project, Guangdong Basic and Applied Basic Research Foundation Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Millimeter-wave (mmWave) radar is widely used for vehicle detection in adverse weather conditions due to its robustness against environmental interference. However, the sparsity of mmWave radar data and the lack of height information significantly limit its broader applicability. To address these challenges, we propose MVDFusion, a multi-modal vehicle detection framework that integrates LiDAR and radar data for robust perception in foggy environments. The proposed framework is designed to fully exploit LiDAR information to compensate for the limitations of sparse radar data. Specifically, two key modules are developed: a radar height query module to enhance height estimation, and a radar–LiDAR query fusion module to improve feature representation. This design enables deep feature-level integration of mmWave radar and LiDAR data. Extensive experiments on the Oxford Radar RobotCar dataset demonstrate that MVDFusion achieves superior performance and robustness under foggy conditions. In particular, it outperforms existing state-of-the-art methods at intersection-over-union thresholds of 0.5, 0.65, and 0.8, achieving detection accuracies of 95.8%, 94.2%, and 81.5%.

Schlagwörter

Stichwörter der Autor:innen

autonomous drivingfoggy weathermillimeter-wave radarsensor fusionvehicle detection

Autor:innen und Institutionen

  • Pengcheng Laboratory, Shenzhen 518055, China.
  • Meteorological Bureau of Shenzhen Municipality, Shenzhen 518040, China.
  • Shenzhen National Climate Observatory, Meteorological Bureau of Shenzhen Municipality, Shenzhen 518040, China.
  • Shenzhen Key Laboratory of Severe Weather in South China, Shenzhen 518040, China.
  • Shenzhen Key Laboratory of Artificial Intelligence for Meteorological Applications Guangzhou, Shenzhen 518040, China.
  • Guangzhou Institute of Tropical and Marine Meteorology, CMA, Guangzhou 510080, China.

ORCID-Profile: Jiake Tian, Yan Gao

Förderung

  • Open Research Project of the CMA Key Laboratory of Hydro-Meteorology Project
  • Science and Technology Project of the Guangdong Meteorological Bureau Project
  • Guangdong Basic and Applied Basic Research Foundation Project
  • the Major Key Project of PCL under Grant
  • Shenzhen Science and Technology Program under Grant
  • Major Key Project of PCL
  • Shenzhen Science and Technology Program

Zitieren

APA

Tian, J., Gao, Y., Xia, X., Ju, G., Ye, P., Tang, S., Wang, H., & Wang, X. (2026). MVDFusion: Multimodal Vehicle Detection in Foggy Weather Using LiDAR and Radar Fusion. Sensors, 26(9), 2663. https://doi.org/10.3390/s26092663

Vancouver

Tian J, Gao Y, Xia X, Ju G, Ye P, Tang S, et al. MVDFusion: Multimodal Vehicle Detection in Foggy Weather Using LiDAR and Radar Fusion. Sensors. 2026;26(9):2663. doi:10.3390/s26092663

BibTeX
@article{Tian2026,
  author = {Tian, Jiake and Gao, Yan and Xia, Xin and Ju, Guoliang and Ye, Peijun and Tang, Sijie and Wang, Hong and Wang, Xucong},
  title = {MVDFusion: Multimodal Vehicle Detection in Foggy Weather Using LiDAR and Radar Fusion},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {9},
  pages = {2663},
  doi = {10.3390/s26092663}
}
Kostenlos starten →