Congestion owing to traffic is one of the crucial complications in urban cities, which is need to be addressed to improve traffic control and operation. The present traffic system is a timer-based system that operates irrespective of the amount of traffic and the existence of emergency vehicles like ambulances and fire engines. Vehicle flow discovery appears to be an important part of modern world traffic control and operation system. This design proposes a novel smart traffic system that utilizes real-time Average Vehicle Area and Emergency vehicle detection to optimize traffic flow and improve emergency response times. This system employs YOLOv4 and MobileNet V2 Convolutional neural network pre-trained model to accurately detect the number of vehicles present on the road, Average Vehicle Area and identify emergency vehicles in real-time. Using this information, this system can dynamically adjust traffic signals and reroute vehicles to minimize congestion and ensure priority access for emergency vehicles. Experimental results show that this system significantly reduces average travel times and emergency response times, making it a promising solution for modern traffic management and emergency services.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Smart Traffic Management System using YOLOv4 and MobileNetV2 Convolutional Neural Network Architecture




    Publication date :

    2023-05-04


    Size :

    7139658 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    German Traffic Sign Recognition Using Convolutional Neural Network

    Santosh, G V S Sree / Kumar, G Chaitanya / Sandeep, G et al. | IEEE | 2022



    Automated Drone Detection Using YOLOv4

    Subroto Singha / Burchan Aydin | DOAJ | 2021

    Free access

    Driver Drowsiness Detection Using NasNet Mobile, MobileNetV2, and EfficientNetB0

    Wunan, Thomas Dante / Jappy, Pretty Calista / Aurelia, Stephanie et al. | IEEE | 2024