Road injuries have been growing every day. Around 8 lakh street injuries occur every 12 months in India on my own. In 2022, it's been mentioned that 4,61,321 avenue accidents were stated and 1,68,491 humans have misplaced their life, i.e., in a mean, 1,263 accidents and 461 deaths each day and nearly 52 injuries and 19 deaths each hour. The fundamental purpose for many of those accidents is rash use, and people are at exquisite risk of controlling rash driving. The proposed solution is to create a tool to manipulate the automobile's velocity based totally on diverse sign boards in the avenue facet. Nowadays, most automobiles are geared up with opposite digicams to get the vehicle's rearview and the front camera to permit the driving force to identify the precise pairing role. The front digital camera inside the cars can be related to the real-time circuit that tracks the sign forums at the road facet. If the vehicle's speed is higher than the authorized variety or if the driving force violates any of the signal boards, he could be warned, and simultaneously, the car's speed will be reduced. Computer imaginative and prescient neural networks and Machine Learning algorithms detect diverse sign forums in the avenue. If the driver violates the rule for the second time, an alert will be dispatched to the nearby visitor's police at the side of the automobile info. By controlling the automobile's velocity, rash driving can be decreased accordingly, and accidents can be averted.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Rash Driver Identification System Using Neural Networks


    Contributors:
    Bhavani, R. (author) / Sabareeswari, T.C (author) / Kandavel, N (author) / Tharun, R (author)


    Publication date :

    2023-12-21


    Size :

    282113 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Driver Identification and Verification From Smartphone Accelerometers Using Deep Neural Networks

    Hernandez Sanchez, Sara / Pozo, Ruben Fernandez / Gomez, Luis Alfonso Hernandez | IEEE | 2022


    Driver identification using 1D convolutional neural networks with vehicular CAN signals

    Hu, Hongyu / Liu, Jiarui / Gao, Zhenhai et al. | Wiley | 2020

    Free access

    Driver identification using 1D convolutional neural networks with vehicular CAN signals

    Hu, Hongyu / Liu, Jiarui / Gao, Zhenhai et al. | IET | 2021

    Free access

    Rash Driving Detection and Alerting System

    Dehankar, Vishwas / Tadse, Surekha | Springer Verlag | 2024


    Driver Drowsiness Detection using Convoluted Neural Networks

    Antony, Nihal / KR, Rohit / Patel, Shreya et al. | IEEE | 2019