Research on Sleep Detection Algorithm during Working Hours Based on Improved YOLOv8s Model

Wanpeng Qi

doi:10.62051/ijcsit.v4n2.38

Authors

Wanpeng Qi

DOI:

https://doi.org/10.62051/ijcsit.v4n2.38

Keywords:

YOLOv8, GAM attention mechanism, WIoU loss function, mAP

Abstract

Sleeping during working hours is not only an uncivilized behavior, but also a serious dereliction of duty and irresponsibility towards the production position. In the production process, if workers sleep during work, it is easy to make mistakes, fail to adjust the working conditions of the machine in a timely manner, and fail to detect problems in the first time, which brings huge safety hazards to the entire production operation and affects production progress. It is indeed a practical problem that should not be ignored. This article proposes a work sleep detection algorithm based on the improved YOLOv8s model to improve detection accuracy and efficiency. After experiments, YOLOv8s was selected as the basis for the algorithm model in this paper. GAM attention mechanism was added to the original YOLOv8s algorithm model, and the loss function WIoUv1 was added. The mAP was increased from the initial 94% to the improved 95%, which provides certain reference value for future algorithm models for detecting sleep during work.

Downloads

Download data is not yet available.

References

[1] Li M, Zhu H, Chen H, et al. Research on object detection algorithm based on deep learning[C]//Journal of Physics: Conference Series. IOP Publishing, 2021, 1995(1): 012046.

[2] Liu Y, Chen H. A Lightweight Container Detection Network Model Based on YOLOv5s[C]//(Technical Committee on Control Theory, Chinese Association of Automation), (Chinese Association of Automation), (Systems Engineering Society of China), (Proceedings of the 42nd Chinese Control Conference). (8). School of Artificial Intelligence, Hebei University of Technology; Control Engineering Technology Innovation Center of Hebei Province, Hebei University of Technology; 2023:6. DOI:10.26914/c.cnkihy.2023.036061.

[3] Du L, Zhang R, Wang X. Overview of two-stage object detection algorithms[C]//Journal of Physics: Conference Series. IOP Publishing, 2020, 1544(1): 012033.

[4] Wang F, Wang H, Qin Z, et al. UAV target detection algorithm based on improved YOLOv8 [J]. IEEE Access, 2023.

[5] Liu Y, Shao Z, Hoffmann N. Global attention mechanism: Retain information to enhance channel-spatial interactions [J]. arxiv preprint arxiv:2112.05561, 2021.