EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Lightweight Helmet Detection Algorithm Using an Improved YOLOv4

Junhua Chen iD, Sihao Deng, Ping Wang, Xueda Huang, Yanfei Liu

Sensors · 21.01.2023 · 23 (3) · 1256

DOI: 10.3390/s23031256 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 21.01.2023. Verfasst von Junhua Chen und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, Natural Science Foundation of Chongqing, China, National Key R&D Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Safety helmet wearing plays a major role in protecting the safety of workers in industry and construction, so a real-time helmet wearing detection technology is very necessary. This paper proposes an improved YOLOv4 algorithm to achieve real-time and efficient safety helmet wearing detection. The improved YOLOv4 algorithm adopts a lightweight network PP-LCNet as the backbone network and uses deepwise separable convolution to decrease the model parameters. Besides, the coordinate attention mechanism module is embedded in the three output feature layers of the backbone network to enhance the feature information, and an improved feature fusion structure is designed to fuse the target information. In terms of the loss function, we use a new SIoU loss function that fuses directional information to increase detection precision. The experimental findings demonstrate that the improved YOLOv4 algorithm achieves an accuracy of 92.98%, a model size of 41.88 M, and a detection speed of 43.23 pictures/s. Compared with the original YOLOv4, the accuracy increases by 0.52%, the model size decreases by about 83%, and the detection speed increases by 88%. Compared with other existing methods, it performs better in terms of precision and speed.

Schlagwörter

Stichwörter der Autor:innen

PP-LCNetSIoUYOLOv4attention mechanismfeature fusionhelmet detection

Autor:innen und Institutionen

  • School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China.
  • Key Laboratory of Industrial Internet of Things & Networked Control, Chongqing University of Posts and Telecommunications, Chongqing 400065, China.
  • School of Artificial Intelligence, Chongqing University of Technology, Chongqing 400054, China.

ORCID-Profile: Junhua Chen

Förderung

  • National Key R&D Program of China
  • Natural Science Foundation of Chongqing, China
  • National Key R&D Program of China

Zitieren

APA

Chen, J., Deng, S., Wang, P., Huang, X., & Liu, Y. (2023). Lightweight Helmet Detection Algorithm Using an Improved YOLOv4. Sensors, 23(3), 1256. https://doi.org/10.3390/s23031256

Vancouver

Chen J, Deng S, Wang P, Huang X, Liu Y. Lightweight Helmet Detection Algorithm Using an Improved YOLOv4. Sensors. 2023;23(3):1256. doi:10.3390/s23031256

BibTeX
@article{Chen2023,
  author = {Chen, Junhua and Deng, Sihao and Wang, Ping and Huang, Xueda and Liu, Yanfei},
  title = {Lightweight Helmet Detection Algorithm Using an Improved YOLOv4},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {3},
  pages = {1256},
  doi = {10.3390/s23031256}
}
Kostenlos starten →