Traffic management has become a tedious task for policemen to carry out manually. According to the publication produced by Bureau of Police Research & Department in 2017, India has just about 72,000 traffic cops to manage almost $20,000,000$ vehicles. As the ratio is insanely high and unmanageable, traffic congestion has increased ever since. Hence, we proposed a smart traffic management system which will particularly tackle this problem using cutting edgetechnology. By analyzing the oncoming traffic, our model predicts the required time for particular vehicles to pass and adjusts the signal timings accordingly. By combining models from deep learning and machine learning we, propose a cheap, efficient system that addresses these problems by a combination of YOLOv8 & Random Forest Regression to generate results. These results consist of annotated images and timings for signals which are calculated from the vehicle count.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Smart Traffic Management: A Deep Learning Approach for Congestion Reduction using YOLOV8 & RandomForest


    Contributors:


    Publication date :

    2024-11-20


    Size :

    688779 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Machine learning Smart Traffic Prediction and Congestion Reduction

    Lakshna, A. / Ramesh, K. / Prabha, B. et al. | IEEE | 2021


    Analysis of Traffic Management System using YOLOv8

    Anvitha, Karnatakam / Sumathi, R. / Vanaja, Kandregula et al. | IEEE | 2023


    Traffic Congestion Detection from Camera Images Using Deep Learning Approach

    Trung, Nguyen Quang / Hai, Phong Bui | Springer Verlag | 2024


    Traffic Congestion Management Using Deep Reinforcement Learning and Decentralized Routing

    Narasimhan, Nirmitii / Mall, Niharika / Rajeev, Advaith M et al. | IEEE | 2024


    Traffic Sign Detection Using YOLOv8

    Kumar, Rahul / Gupta, Aniket / D, Rajeswari | IEEE | 2024