EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A PPE detection method based on the advanced YOLOv11 architecture with a lightweight refinement block system

Alibek Barlybayev, Nurzada Amangeldy, Bijeesh Kozhikkodan Veettil iD, Bekbolat Kurmetbek, Akmaral Kassymova, Ramazan Sadvakassov

PLOS One · 10.11.2026 · 21 (11) · e0361911

DOI: 10.1371/journal.pone.0361911 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 10.11.2026. Verfasst von Alibek Barlybayev und 5 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Information Technologies, L.N. Gumilyov Eurasian National University, Astana, Kazakhstan. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Higher Education of the Republic of Kazakhstan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated monitoring of personal protective equipment usage is crucial due to the high incidence of accidents in the construction industry, with over half attributed to the improper use of protective equipment. Existing deep learning models show limited performance in detecting small-scale objects and reduced accuracy under challenging visual conditions. To address these limitations, this study introduces YOLOv11s-R 3 , an enhanced version of the YOLOv11s architecture with a P2-focused refinement block. The proposed model extends the standard feature pyramid network to stride-4 resolution and applies a single lightweight C2f block on the P2 feature map, targeting fine-scale objects. The model was trained on the Color Helmet and Vest dataset and evaluated on its held-out test split and on the GDUT Hardhat Wearing Detection dataset, with all experiments repeated across five independent random seeds. On the CHV test split, YOLOv11s-R 3 achieved a precision of 0.9103 and mAP@50 of 0.9032, compared to 0.9035 and 0.9011 for the YOLOv11s baseline. The model maintained an inference speed of approximately 5 ms per image (190 FPS on an NVIDIA Quadro RTX 6000 GPU). On the CHV test split, the observed mAP@0.5 gain was not statistically distinguishable from run-to-run variance (paired t-test, p = 0.369). In contrast, the improvement observed on GDUT-HWD was more consistent relative to run-to-run variance, providing the primary evidence that the benefit of the proposed refinement extends across datasets. Together with an inference speed of approximately 5 ms per image, these findings support the applicability of YOLOv11s-R 3 to real-time PPE monitoring.

Autor:innen und Institutionen

  • Faculty of Information Technologies, L.N. Gumilyov Eurasian National University, Astana, Kazakhstan.
  • SignBridge LLP, Astana, Kazakhstan.
  • Laboratory of Ecology and Environmental Management, Science and Technology Advanced Institute, Van Lang University, Ho Chi Minh City, Vietnam.
  • Faculty of Applied Technology, Van Lang School of Technology, Van Lang University, Ho Chi Minh City, Vietnam.
  • Institute of Economics, Information Technologies and Professional Education, Zangir Khan West Kazakhstan Agrarian-Technical University, Uralsk, Kazakhstan.

ORCID-Profile: Bijeesh Kozhikkodan Veettil

Förderung

  • Ministry of Science and Higher Education of the Republic of Kazakhstan

Zitieren

APA

Barlybayev, A., Amangeldy, N., Veettil, B. K., Kurmetbek, B., Kassymova, A., & Sadvakassov, R. (2026). A PPE detection method based on the advanced YOLOv11 architecture with a lightweight refinement block system. PLOS One, 21(11), e0361911. https://doi.org/10.1371/journal.pone.0361911

Vancouver

Barlybayev A, Amangeldy N, Veettil BK, Kurmetbek B, Kassymova A, Sadvakassov R. A PPE detection method based on the advanced YOLOv11 architecture with a lightweight refinement block system. PLOS One. 2026;21(11):e0361911. doi:10.1371/journal.pone.0361911

BibTeX
@article{Barlybayev2026,
  author = {Barlybayev, Alibek and Amangeldy, Nurzada and Veettil, Bijeesh Kozhikkodan and Kurmetbek, Bekbolat and Kassymova, Akmaral and Sadvakassov, Ramazan},
  title = {A PPE detection method based on the advanced YOLOv11 architecture with a lightweight refinement block system},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {11},
  pages = {e0361911},
  doi = {10.1371/journal.pone.0361911}
}
Kostenlos starten →