EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EdgeCaseDNet: An enhanced detection architecture for edge case perception in autonomous driving

Yin Lei iD, Chen Shan, Wancheng Ge

PLOS One · 2025

DOI: 10.1371/journal.pone.0338638 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Yin Lei und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Electronic and Information Engineering, Tongji University, Shanghai, China. Hauptthemen laut MEDLINE: Automobile Driving. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Innovative Research Group Project of the National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Autonomous driving perception systems still encounter significant challenges in edge scenarios involving multi-scale target changes and adverse weather, which seriously compromise detection reliability. To address this issue, we introduce a novel edge case dataset that extends existing benchmarks by capturing extreme road conditions (fog, rain, snow, nighttime et al.) with precise annotations, and develop EdgeCaseDNet as an optimized object-detection framework. EdgeCaseDNet’s architecture extends YOLOv8 through four synergistic innovations: (1) a Haar_HGNetv2 backbone that enables hierarchical feature extraction with enhanced long-range dependencies, (2) an asymptotic feature pyramid network for context-aware multi-scale fusion, (3) a hybrid partial depth-wise separable convolution module, and (4) Wise-IoU loss optimization for accelerated convergence. Comprehensive evaluations demonstrated the superiority of EdgeCaseDNet over YOLOv8, achieving improvements of +10.6% in mAP@50, and +8.4% in mAP@[.5:.95]. All the relevant codes are available at https://github.com/yutianku/EdgeCaseDNet .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Automobile DrivingHumansAlgorithmsWeather

Autor:innen und Institutionen

  • College of Electronic and Information Engineering, Tongji University, Shanghai, China.

ORCID-Profile: Yin Lei

Förderung

  • Innovative Research Group Project of the National Natural Science Foundation of China

Zitieren

APA

Lei, Y., Shan, C., & Ge, W. (2025). EdgeCaseDNet: An enhanced detection architecture for edge case perception in autonomous driving. PLOS One. https://doi.org/10.1371/journal.pone.0338638

Vancouver

Lei Y, Shan C, Ge W. EdgeCaseDNet: An enhanced detection architecture for edge case perception in autonomous driving. PLOS One. 2025. doi:10.1371/journal.pone.0338638

BibTeX
@article{Lei2025,
  author = {Lei, Yin and Shan, Chen and Ge, Wancheng},
  title = {EdgeCaseDNet: An enhanced detection architecture for edge case perception in autonomous driving},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0338638}
}
Kostenlos starten →