Using state-of-the-art computer vision techniques, a model was designed to be able to detect fatigue in haul truck drivers in South American mines. The proposed solution uses a DNN-based (Deep Neural Networks) face detection model, caffe, to detect the presence of the driver’s face and a facial landmark detection model of MobileNetV2 architecture to identify key features of the face. Afterwards, the eye aspect ratio (EAR) and the mouth aspect ratio (MAR) are calculated, which are then used to calculate the percent eye-closure over a time period (PERCLOS), blink rates and duration, yawns, distraction, and other indicators. The results successfully detect fatigue symptoms over 72% of the times on haul truck drivers in Peruvian mines.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Using facial landmarks to detect driver fatigue


    Contributors:
    Martinez, A. (author) / Berrospi, F. (author) / Porras, V. (author) / Portocarrero, M. (author)


    Publication date :

    2022-08-11


    Size :

    9973435 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Driver State Alert Control using Head Shoulder Inclination and Facial Landmarks

    Ashitha Ebrahim / Fathimathul Harshima P. T. / Aby Abahai T | BASE | 2020

    Free access

    Facial Landmarks Based Drowsy Driver Detection Model with OpenCV and DLib

    N, Karthikeyan / D, Mansoor Hussain / Varma, M. Rishit et al. | IEEE | 2023


    Predict Driver Fatigue Using Facial Features

    Berkati, Oussama / Srifi, Mohamed Nabil | IEEE | 2018


    Eye Fatigue Detection in Vehicle Drivers Based on Facial Landmarks Features

    Fikriyah, Fia Dumi Hasanatul / Nugroho, Anan / Suni, Alfa Faridh | BASE | 2021

    Free access

    Monitoring Driver Fatigue Using Facial Analysis Techniques

    Singh, S. / Papanikolopoulos, N. P. / IEEE et al. | British Library Conference Proceedings | 1999