EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Advancing construction safety: YOLOv8-CGS helmet detection model

Zhihui Wu, Xiaojia Lei iD, Munish Kumar

PLOS One · 20.05.2025 · 20 (5) · e0321713

DOI: 10.1371/journal.pone.0321713 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 20.05.2025. Verfasst von Zhihui Wu und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Civil Engineering, Anhui Communications Vocational & Technical College, Hefei, China. Hauptthemen laut MEDLINE: Head Protective Devices, Construction Industry, Models, Theoretical. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Anhui Province Higher Education Science Research Project (Natural Science Category) Research on Site Monitoring and Safety Warning Technology Based on AI Recog….

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the context of construction site safety management, real-time object detection is crucial for ensuring workers’ safety through accurate detection of safety helmets. However, traditional object detection methods often face numerous challenges in complex construction environments, such as low light, occlusion, and the diverse shapes of helmets. To address these issues, we propose an improved helmet detection model, YOLOv8-CGS , which is based on the YOLOv8 architecture and integrates optimization modules such as CBAM (Convolutional Block Attention Module), GAM (Global Attention Mechanism), and SLOU (Smooth Labeling Loss Function). The goal is to enhance the model’s detection accuracy and robustness in complex scenarios. Specifically, GAM improves the model’s attention to key regions, CBAM enhances its ability to perceive important features, and SLOU optimizes the accuracy of bounding box predictions, particularly in complex and occluded environments. Experimental results show that YOLOv8-CGS achieves accuracy rates of 94.58% and 92.38% on the SHD and SHWD datasets, respectively, which represent improvements of 5.9% and 5.94% compared to YOLOv8 . This enhancement allows YOLOv8-CGS to provide more efficient and accurate helmet detection in practical applications, significantly improving the real-time monitoring capabilities for construction site safety management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Head Protective DevicesConstruction IndustryModels, TheoreticalHumansAlgorithms

Autor:innen und Institutionen

  • Department of Civil Engineering, Anhui Communications Vocational & Technical College, Hefei, China.
  • School of Petrochemical Engineering, Hunan Petrochemical Vocational and Technical College, Yueyang, China.
  • Maharaja Ranjit Singh Punjab Technical University, Punjab, India.

ORCID-Profile: Xiaojia Lei

Förderung

  • Anhui Province Higher Education Science Research Project (Natural Science Category) Research on Site Monitoring and Safety Warning Technology Based on AI Recog…

Zitieren

APA

Wu, Z., Lei, X., & Kumar, M. (2025). Advancing construction safety: YOLOv8-CGS helmet detection model. PLOS One, 20(5), e0321713. https://doi.org/10.1371/journal.pone.0321713

Vancouver

Wu Z, Lei X, Kumar M. Advancing construction safety: YOLOv8-CGS helmet detection model. PLOS One. 2025;20(5):e0321713. doi:10.1371/journal.pone.0321713

BibTeX
@article{Wu2025,
  author = {Wu, Zhihui and Lei, Xiaojia and Kumar, Munish},
  title = {Advancing construction safety: YOLOv8-CGS helmet detection model},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {5},
  pages = {e0321713},
  doi = {10.1371/journal.pone.0321713}
}
Kostenlos starten →