Distracted driving remains a leading cause of traffic accidents, with an increasing number of fatalities each year. Therefore, the aim of this study is to design and develop a driver monitoring system (DMS) based on an enhanced YOLOv5 algorithm. This system enables real-time monitoring of the driver’s physiological state using integrated intelligent examination equipment placed in the steering wheel, which connects to the central control computer, mobile phone, and PC. The system records and analyzes health data, identifies potential health risks and fatigue levels, and ensures the driver’s safety. Additionally, this study developed a distracted driving detection model and trained it using YOLOv5. The results demonstrate that the model achieves an impressive 98% accuracy in detecting driver distraction. Furthermore, the LightGBM classification metrics show an accuracy of 0.9738, a recall rate of 0.9736, and an F1 score of 0.9735, further confirming the system’s high performance and effectiveness. The findings offer significant advantages for driver monitoring in intelligent cockpit environments and present new ideas and methodologies for research in related fields.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research and application of driver DMS detection based on improved YOLOv5 algorithm


    Contributors:
    Kolhe, Mohan (editor) / Gou, Bin (editor) / Zhou, You (author) / Ni, Wentao (author) / Ding, Jiahao (author) / Huang, Yixuan (author) / Zhang, Jingwen (author) / Li, Yunpeng (author) / Wu, Chou (author)

    Conference:

    International Conference on Electrical Engineering and Intelligent Systems (IC2EIS 2025) ; 2025 ; Chengdu, China


    Published in:

    Proc. SPIE ; 13696 ; 136960U


    Publication date :

    2025-08-01





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Lightweight pear detection algorithm based on improved YOLOv5

    Hu, Xiaomei / Zhang, Yunyou / Chen, Yi et al. | SPIE | 2023




    Mixed Traffic Flow Detection Algorithm Based on Improved YOLOv5

    Wang, Zhiyong / Lv, Bin / Chen, Qixiang | Springer Verlag | 2025


    Detection of Driver Distraction using YOLOv5 Network

    Atas, Kubilay / Vural, Revna Acar | IEEE | 2021