EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PF-ConvNeXt: An Adverse Weather Recognition Network for Autonomous Driving Scenes

Quanxiang Wang, Zhaofa Zhou, Zhili Zhang

Electronics · 24.02.2026 · 15 (5) · 920

DOI: 10.3390/electronics15050920 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 24.02.2026. Verfasst von Quanxiang Wang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation of China, the Shaanxi Province Science and Technology Innovation Team Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rain, snow, fog, and dust can degrade road-scene images, blur fine details, and consequently reduce the reliability of perception systems for autonomous driving. To address this problem, this paper proposes PF-ConvNeXt, an adverse weather recognition model built upon the ConvNeXt architecture. First, a lightweight pyramid split attention (PSA) module is introduced to enable multi-scale feature fusion, so that both global degradation patterns and local texture details can be captured simultaneously. Second, a feature enhancement channel and spatial attention module (FECS) is designed. It adaptively recalibrates features along the channel and spatial paths, thereby suppressing interference from complex backgrounds and noise. Third, during training, Focal Loss is adopted to strengthen learning for hard samples and minority weather categories, alleviating recognition bias caused by class imbalance. Experiments are conducted on a dataset of 5000 images constructed by integrating RTTS, DAWN, and a self-collected rainy-weather dataset. The results show that PF-ConvNeXt achieves 90.16% accuracy, 95.24% mean average precision, and a 92.18% F1-score. It outperforms the ConvNeXt baseline by 4.74%, 5.46%, and 5.95%, respectively, and surpasses multiple mainstream classification models. This study provides an effective recognition framework for robust environmental perception under challenging weather conditions and demonstrates promising potential for practical deployment.

Förderung

  • the National Natural Science Foundation of China
  • the Shaanxi Province Science and Technology Innovation Team Project

Zitieren

APA

Wang, Q., Zhou, Z., & Zhang, Z. (2026). PF-ConvNeXt: An Adverse Weather Recognition Network for Autonomous Driving Scenes. Electronics, 15(5), 920. https://doi.org/10.3390/electronics15050920

Vancouver

Wang Q, Zhou Z, Zhang Z. PF-ConvNeXt: An Adverse Weather Recognition Network for Autonomous Driving Scenes. Electronics. 2026;15(5):920. doi:10.3390/electronics15050920

BibTeX
@article{Wang2026,
  author = {Wang, Quanxiang and Zhou, Zhaofa and Zhang, Zhili},
  title = {PF-ConvNeXt: An Adverse Weather Recognition Network for Autonomous Driving Scenes},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {5},
  pages = {920},
  doi = {10.3390/electronics15050920}
}
Kostenlos starten →