With the modern population boom in cities, traffic congestion has become an ever-present issue that worsens constantly. To tackle this critical issue, accurate predictions of traffic based on real-world trends are needed to anticipate traffic and take appropriate measures. To fulfil this, in this paper, we have used vehicle detection based on the YOLO model and Time-Series Forecasting based on the traffic detected over some time to identify the traffic trends and predict the future accordingly. By forecasting the traffic for the day on an intersection using traffic data extrapolated from the vehicle Detection model collected historically, we aim to provide high accurate Predictions of traffic congestion.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Advanced Traffic Surveillance: YOLO-ARIMA Hybrid for Real-Time Monitoring


    Beteiligte:


    Erscheinungsdatum :

    04.10.2024


    Format / Umfang :

    1127236 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Traffic Surveillance System Using YOLO Algorithm and Machine Learning

    Giri, Shiva Rama Krishna Shira / P, Logesh / S, Barath Sundar et al. | IEEE | 2023


    A Real-Time Malaysian Traffic Sign Recognition Using YOLO Algorithm

    Mangshor, Nur Nabilah Abu / Paudzi, Nurul Paudziah Aida Mohd / Ibrahim, Shafaf et al. | Springer Verlag | 2021


    A Real-Time Malaysian Traffic Sign Recognition Using YOLO Algorithm

    Abu Mangshor, Nur Nabilah / Paudzi, Nurul Paudziah Aida Mohd / Ibrahim, Shafaf et al. | British Library Conference Proceedings | 2022



    Video sensor network for real-time traffic monitoring and surveillance

    Semertzidis, T. / Dimitropoulos, K. / Koutsia, A. et al. | IET | 2010