Drowsiness has become a major problem in people’s lives, resulting in ineffective work or traffic accidents. Every year the rate of injuries and accidents increases due to the drowsiness of drivers around the world. Therefore, developing a real-time driver drowsiness detection system is a current necessity. This paper presents a real-time driver drowsiness detection scheme (RealD3) that uses advanced machine learning algorithms for prediction. The main aim of this work is to detect and analyze the facial structure and objects in the frame. To capture the driver’s face, a camera-based video-capturing mechanism is used. Mediapipe face mesh 468 and YOLO (You Only Look Once) are used for detecting landmarks and facial features in the frame, respectively. Once face, landmark, and facial features (such as Eye Aspect Ratio (EAR), Mouth Aspect Ratio (MAR), Hands on Mouth, and if sunglasses are worn or not ) get detected, PERCLOS is used for classifying if the driver is drowsy or simply blinking. An alert is given to the driver when the EAR and MAR values are less than the threshold value and YOLO detects drowsiness based on the facial features. The real-time experimental results show that the proposed method is highly accurate and advanced, with an overall accuracy of about 94% in detecting drowsiness and identifying objects in the frame.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    RealD3: A Real-time Driver Drowsiness Detection Scheme Using Machine Learning


    Beteiligte:
    Rathod, Siddharajsinh (Autor:in) / Mali, Trushil (Autor:in) / Jogani, Yash (Autor:in) / Faldu, Nil (Autor:in) / Odedra, Vidit (Autor:in) / Barik, Pradip Kumar (Autor:in)


    Erscheinungsdatum :

    2023-06-07


    Format / Umfang :

    1931804 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Real-Time Driver Drowsiness Detection System Using Machine Learning

    Roy, Apash / Ghosh, Debayani | Springer Verlag | 2023


    Driver Drowsiness Detection Using Machine Learning

    Ritesh, Aryan / Jagatia, Neel / Deshmukh, Pankaj | IEEE | 2023


    Snooze Breaker: Driver Drowsiness Detection Using Machine Learning

    Rao, Sinchana N / Sunitha, N. / Swathi, M S et al. | Springer Verlag | 2021



    Driver Drowsiness Detection Using Deep Learning

    Ojha, Dhiren / Pawar, Amit / Kasliwal, Gaurav et al. | IEEE | 2023