EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

High-Precision and Lightweight Model for Rapid Safety Helmet Detection

Xuejun Jia, Xiaoxiong Zhou, Chunyi Su, Zhihan Shi, Xiaodong Lv iD, Chao Lu, Guangming Zhang iD

Sensors · 30.10.2024 · 24 (21) · 6985

DOI: 10.3390/s24216985 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 30.10.2024. Verfasst von Xuejun Jia und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing 211816, China. Hauptthemen laut MEDLINE: Head Protective Devices. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents significant improvements in the accuracy and computational efficiency of safety helmet detection within industrial environments through the optimization of the you only look once version 5 small (YOLOv5s) model structure and the enhancement of its loss function. We introduce the convolutional block attention module (CBAM) to bolster the model’s sensitivity to key features, thereby enhancing detection accuracy. To address potential performance degradation issues associated with the complete intersection over union (CIoU) loss function in the original model, we implement the modified penalty-decay intersection over union (MPDIoU) loss function to achieve more stable and precise bounding box regression. Furthermore, considering the original YOLOv5s model’s large parameter count, we adopt a lightweight design using the MobileNetV3 architecture and replace the original squeeze-and-excitation (SE) attention mechanism with CBAM, significantly reducing computational complexity. These improvements reduce the model’s parameters from 15.7 GFLOPs to 5.7 GFLOPs while increasing the mean average precision (mAP) from 82.34% to 91.56%, demonstrating its superior performance and potential value in practical industrial applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Head Protective DevicesHumansAlgorithmsModels, TheoreticalEquipment Design

Stichwörter der Autor:innen

CBAM attention mechanismMPDIoU loss functionYOLOv5ssafety helmet detection

Autor:innen und Institutionen

  • College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing 211816, China.
  • China Construction Second Engineering Bureau Co., Ltd., Beijing 100160, China.

ORCID-Profile: Xiaodong Lv, Guangming Zhang

Zitieren

APA

Jia, X., Zhou, X., Su, C., Shi, Z., Lv, X., Lu, C., & Zhang, G. (2024). High-Precision and Lightweight Model for Rapid Safety Helmet Detection. Sensors, 24(21), 6985. https://doi.org/10.3390/s24216985

Vancouver

Jia X, Zhou X, Su C, Shi Z, Lv X, Lu C, et al. High-Precision and Lightweight Model for Rapid Safety Helmet Detection. Sensors. 2024;24(21):6985. doi:10.3390/s24216985

BibTeX
@article{Jia2024,
  author = {Jia, Xuejun and Zhou, Xiaoxiong and Su, Chunyi and Shi, Zhihan and Lv, Xiaodong and Lu, Chao and Zhang, Guangming},
  title = {High-Precision and Lightweight Model for Rapid Safety Helmet Detection},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {21},
  pages = {6985},
  doi = {10.3390/s24216985}
}
Kostenlos starten →