EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DPF-YOLOv8: Dual Path Feature Fusion Network for Traffic Sign Detection in Hazy Weather

Yuechong Zhang, Haiying Liu, Dehao Dong, Xuehu Duan, Fei Lin, Zengxiao Liu

Electronics · 12.10.2024 · 13 (20) · 4016

DOI: 10.3390/electronics13204016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 12.10.2024. Verfasst von Yuechong Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Innovation Ability Enhancement Project of Shandong Province Science and Technology Small and Medium Enterprises, Research and Application of Key Technologies f…, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traffic sign detection plays an integral role in intelligent driving systems. It was found that in real driving scenarios, traffic signs were easily obscured by haze leading to traffic sign detection inaccuracy in assisted driving systems. Therefore, we designed a traffic sign detection model for hazy weather that can effectively help drivers to recognize road signs and reduce the incidence of traffic accidents. A high-precision traffic sign detection network has been designed to address the problem of decreased model recognition performance caused by external factors such as small size of traffic signs and haze obstruction in real-world scenarios. First, the default YOLOv8 was found to have low model detection accuracy in hazy weather occlusion conditions through experimental studies. Therefore, a deeper lightweight and efficient multi-branch CSP (Cross Stage Partial) module was introduced. Second, a dual path feature fusion network was designed to address the problem of insufficient feature fusion due to the small size of traffic signs. Finally, in order to be able to better simulate the real haze weather scene, we added fog to the raw data to enrich the data samples. This was verified through experiments on a public Chinese traffic sign detection dataset after fogging treatment, compared to the default YOLOv8 model. The improved DPF-YOLOv8 algorithm achieved 2.1% and 2.2% improvement in mAP@0.5 and mAP@0.5:0.95 performance metrics to 65.0% and 47.4%, respectively.

Förderung

  • Innovation Ability Enhancement Project of Shandong Province Science and Technology Small and Medium Enterprises, Research and Application of Key Technologies f…
  • National Natural Science Foundation of China

Zitieren

APA

Zhang, Y., Liu, H., Dong, D., Duan, X., Lin, F., & Liu, Z. (2024). DPF-YOLOv8: Dual Path Feature Fusion Network for Traffic Sign Detection in Hazy Weather. Electronics, 13(20), 4016. https://doi.org/10.3390/electronics13204016

Vancouver

Zhang Y, Liu H, Dong D, Duan X, Lin F, Liu Z. DPF-YOLOv8: Dual Path Feature Fusion Network for Traffic Sign Detection in Hazy Weather. Electronics. 2024;13(20):4016. doi:10.3390/electronics13204016

BibTeX
@article{Zhang2024,
  author = {Zhang, Yuechong and Liu, Haiying and Dong, Dehao and Duan, Xuehu and Lin, Fei and Liu, Zengxiao},
  title = {DPF-YOLOv8: Dual Path Feature Fusion Network for Traffic Sign Detection in Hazy Weather},
  journal = {Electronics},
  year = {2024},
  volume = {13},
  number = {20},
  pages = {4016},
  doi = {10.3390/electronics13204016}
}
Kostenlos starten →