Intelligent monitoring model of wearing of industrial safety protective equipment based on YOLOv8 algorithm

Industrial safety is essential for the reliability and sustainability of production operations. In this study, a safety protective equipment detection scheme based on YOLOv8 algorithm is proposed for industrial security scenarios. By optimizing the lightweight strategy and updating the weight of the...

Full description

Saved in:
Bibliographic Details
Published in2023 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) pp. 1022 - 1030
Main Authors Lin, Zaixin, Huang, Zihui, Yuan, Jiayou, Pan, Xinxin
Format Conference Proceeding
LanguageEnglish
Published IEEE 03.11.2023
Subjects
edge computing
industrial safety
Monitoring
Real-time systems
Reliability
Safety
SEAttention
Security
Shufflenetv 2
Sustainable development
Task analysis
YOLOv8
Online AccessGet full text

Cover

More Information
Summary:Industrial safety is essential for the reliability and sustainability of production operations. In this study, a safety protective equipment detection scheme based on YOLOv8 algorithm is proposed for industrial security scenarios. By optimizing the lightweight strategy and updating the weight of the original YOLOv8 model, a more efficient network architecture is adopted, which reduces the complexity of the model while ensuring detection accuracy, and deploys the lightweight model on edge applications. Experimental results show that the optimized lightweight model achieves 94% of the mAP50 values on the detection tasks of four types of safety protective equipment, and can be monitored in real time at a speed of 17 frames per second, achieving a good balance between accuracy and efficiency. This study provides a low-complexity, high-efficiency intelligent detection system scheme for industrial safety monitoring.
DOI:10.1109/ICICML60161.2023.10424956