EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

YOLO-AFL: A Novel Lightweight Algorithm for Real-Time Safety Helmet Detection in Factory Workshops

Hao Wang iD, Xianying Feng iD, Peigang Li, Anning Wang, Ming Yao

Sensors · 20.05.2026 · 26 (10) · 3237

DOI: 10.3390/s26103237 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 20.05.2026. Verfasst von Hao Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Shandong University, Jinan 250061, China. Hauptthemen laut MEDLINE: Algorithms, Head Protective Devices. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Department of Science and Technology of Shandong Province, Key Technology Research and Development Program of Shandong.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In factory workshops, wearing safety helmets is vital for worker safety. However, current deep learning-based detection methods are often hindered by large model parameters and high computational demands, limiting their deployment in resource-constrained settings. This article introduces YOLO-AFL, a novel lightweight model designed to solve these problems. The algorithm introduces several key optimizations to improve performance without increasing computational load. Firstly, the K-Means++ algorithm is applied during the anchor box preprocessing stage, along with a new distance metric (1 − AIoU), which enhances anchor box size estimation and boosts performance without additional overhead. Secondly, by introducing a lightweight PConv operation into the C3 module, the complexity of the model is significantly reduced. Finally, a dual attention network (LDA-GC) is designed to compensate for any accuracy loss caused by the model’s simplifications. Experimental results on a custom dataset show that the proposed algorithm achieves an mAP50 of 94.1%. Compared to the baseline model, it reduces the number of parameters by 19.1% and decreases computational complexity by 16.9%, demonstrating its superior performance and efficiency in safety helmet wearing detection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsHead Protective DevicesDetection AlgorithmsHumans

Stichwörter der Autor:innen

YOLOlightweight modelsafety helmettarget detection

Autor:innen und Institutionen

  • School of Mechanical Engineering, Shandong University, Jinan 250061, China.
  • Key Laboratory of High Efficiency and Clean Mechanical Manufacture of Ministry of Education, Shandong University, Jinan 250061, China.

ORCID-Profile: Hao Wang, Xianying Feng

Förderung

  • National Natural Science Foundation of China
  • Department of Science and Technology of Shandong Province
  • Key Technology Research and Development Program of Shandong

Zitieren

APA

Wang, H., Feng, X., Li, P., Wang, A., & Yao, M. (2026). YOLO-AFL: A Novel Lightweight Algorithm for Real-Time Safety Helmet Detection in Factory Workshops. Sensors, 26(10), 3237. https://doi.org/10.3390/s26103237

Vancouver

Wang H, Feng X, Li P, Wang A, Yao M. YOLO-AFL: A Novel Lightweight Algorithm for Real-Time Safety Helmet Detection in Factory Workshops. Sensors. 2026;26(10):3237. doi:10.3390/s26103237

BibTeX
@article{Wang2026,
  author = {Wang, Hao and Feng, Xianying and Li, Peigang and Wang, Anning and Yao, Ming},
  title = {YOLO-AFL: A Novel Lightweight Algorithm for Real-Time Safety Helmet Detection in Factory Workshops},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {3237},
  doi = {10.3390/s26103237}
}
Kostenlos starten →