Existing methodologies to count vehicles from a road image have depended upon both hand-crafted feature engineering and rule-based algorithms. These require many predefined thresholds to detect and track vehicles. This paper provides a supervised learning methodology that requires no such feature engineering. A deep convolutional neural network was devised to count the number of vehicles on a road segment based solely on video images. The present methodology does not regard an individual vehicle as an object to be detected separately; rather, it collectively counts the number of vehicles as a human would. The test results show that the proposed methodology outperforms existing schemes.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Image-Based Learning to Measure Traffic Density Using a Deep Convolutional Neural Network


    Beteiligte:
    Chung, Jiyong (Autor:in) / Sohn, Keemin (Autor:in)


    Erscheinungsdatum :

    01.05.2018


    Format / Umfang :

    1535578 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Traffic Density Estimation and Traffic Control using Convolutional Neural Network

    Ikiriwatte, A.K. / Perera, D.D.R. / Samarakoon, S.M.M.C. et al. | IEEE | 2019


    Traffic Density Estimation using a Convolutional Neural Network

    Nubert, Julian / Truong, Nicholas Giai / Lim, Abel et al. | ArXiv | 2018

    Freier Zugriff

    Density Based Traffic Control System with Convolutional Neural Network

    Saple Mrunali R. / Jadhav Tejaswini M. / Kode Saurabh Y. et al. | DOAJ | 2022

    Freier Zugriff

    Robust Traffic Signs Classification using Deep Convolutional Neural Network

    Kherraki, Amine / Maqbool, Muaz / Ouazzani, Rajae El | IEEE | 2022