AI Sentinel is a groundbreaking project aimed at revolutionizing road safety through the use of cutting-edge deep learning technology to enhance driver awareness. Given the significant role of driver drowsiness in road accidents, there is an urgent need for efficient real-time detection systems for preventive measures. This paper introduces a novel Python-based system for detecting driver drowsiness, leveraging the OpenCV library for Face Eye Detection implementation. By focusing on the color characteristics of the face and utilizing a camera to capture facial expressions, the system identifies signs of fatigue. OpenCV, known for its prowess in computer vision tasks, is the primary technology employed in this system, enabling accurate detection of drowsiness indicators, particularly in the eyes. The system’s real time functionality ensures prompt responses to the driver’s condition, effectively mitigating the risk of accidents. Through meticulous analysis of facial characteristics, the system can detect subtle changes indicative of drowsiness, issuing timely warnings to the driver to stop or take a break, thus reducing the likelihood of accidents. The proactive design of the system makes it a valuable tool for enhancing traffic safety. Experimental results validate the effectiveness of the proposed approach in accurately detecting driver drowsiness and delivering real-time notifications, underscoring its potential to significantly reduce traffic incidents caused by fatigued drivers. The practical relevance of the system in addressing road safety challenges is emphasized by its ability to identify drowsiness and issue timely warnings, positioning it as a proactive solution to minimize road accidents caused by inattentive driving. Overall, this study contributes to advancing traffic safety by introducing a reliable method for real-time detection of drowsy driving, leveraging colorful facial traits analysis and OpenCV technology integrated with Python programming.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Deep Learning for Driver Vigilance and Road Safety


    Beteiligte:
    Kaushik, Priyanka (Autor:in) / Yadav, Khushbu (Autor:in) / C, Sincija (Autor:in) / Gopika, B.S. (Autor:in) / Kumar, Narendra (Autor:in) / Kaushik, Manas Manglik (Autor:in)


    Erscheinungsdatum :

    22.11.2024


    Format / Umfang :

    554832 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Driver vigilance monitoring - new developments

    Boverie, S. / Daurenjou, D. / Esteve, D. et al. | Tema Archiv | 2002


    DrowseGuard – DeepAlert Driver Vigilance System

    Awachat, Snehal / Mundada, Krishna / Dewangan, Parag et al. | IEEE | 2024


    Driver Drowsiness Detection for Road Safety Using Deep Learning

    Saini, Parul / Kumar, Krishan / Kashid, Shamal et al. | Springer Verlag | 2023


    Driver vigilance reminding circuit and system

    ZHAO HONG / ZHANG WENWEN / LIU GUOFEI et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    DEVICE FOR CONTROL OVER DRIVER VIGILANCE

    BELOVA TAT JANA IVANOVNA / SUKHOV SERGEJ SERGEEVICH / GAVRISHCHUK VLADIMIR IVANOVICH et al. | Europäisches Patentamt | 2015

    Freier Zugriff