Driver fatigue is a leading cause of road accidents. This research presents a real-time driver drowsiness detection system using deep learning, optimized for low-power embedded systems. By compressing a complex model into a lightweight version, the system achieves an 85.5% accuracy in detecting various alertness states while maintaining energy efficiency. Utilizing facial landmark tracking and the Haar-Cascade method, the approach ensures fast and accurate detection, making it ideal for real-time vehicle safety applications. The system's integration into modern vehicles promises enhanced driver fatigue management and accident prevention.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Real-Time Driver Alertness Monitoring with Optimized Deep Learning and Haar-Cascade Methods


    Contributors:


    Publication date :

    2024-11-22


    Size :

    638716 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Real-Time Driver Alertness Assessment Using Neural Networks

    M, Yoga / M, Ramyasri M / R, Lokitha et al. | IEEE | 2025


    Driver alertness sensing

    Holzbecher, J. / Holzmann, F. / Bellino, M. et al. | IEEE | 2006


    Driver alertness monitoring techniques: a literature review

    Culp, J. / El Gindy, M. | Tema Archive | 2008


    Monitoring driver alertness using unobtrusive psychophysiological measures

    Stein, A. C. | British Library Conference Proceedings | 1996


    Driver alertness monitoring techniques: a literature review

    Culp,J. / El Gindy,M. / Haque,A. et al. | Automotive engineering | 2008