Accurate vehicle count prediction enables intelligent traffic signal control, dynamic route planning, and improved public transportation scheduling, all of which contribute to smoother traffic flow. In a smart city ecosystem, this data-driven approach enhances mobility, reduces carbon emissions, and improves overall urban infrastructure efficiency. Traditional vehicle count prediction methods, such as manual surveys and sensor-based systems, have long been used to estimate vehicle counts. As cities grow, the need for scalable and accurate solutions to estimate vehicle count has become increasingly critical. By leveraging AI-powered models vehicle count at different locations and times can be accurately measured in real-time, allowing traffic authorities to take proactive measures to monitor traffic. This paper introduces an AI-powered model for real-time vehicle count prediction, capable of accurately identifying and classifying vehicles. The model is trained on real-time data provided by Tumkur Smart City Limited, Tumkur—a district in Karnataka recognized under India's Smart City Scheme. Making use of the YOLOv8, an object detection algorithm that uses a single neural network for real-time object detection, which is known for its comprehensive capabilities. The AI-powered VCP model ensures speed and accuracy, making it an optimal choice for real-time object detection and ecosystem integration thereby supporting sustainable transportation. The model demonstrates excellent performance in vehicle identification and classification, achieving a 99% mAP score across all defined classes by offering an efficient and scalable solution for traffic control in smart cities.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    AI-Powered Vehicle Count Prediction for Smart City Traffic Management


    Beteiligte:
    N, Hemavathi (Autor:in) / Sumathi, R (Autor:in) / R M, Savithramma (Autor:in)


    Erscheinungsdatum :

    28.05.2025


    Format / Umfang :

    929976 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Smart city traffic management system

    Europäisches Patentamt | 2025

    Freier Zugriff

    Smart traffic management system for smart city

    YE QINFA / TANG QING / ZHU WANRONG | Europäisches Patentamt | 2023

    Freier Zugriff

    Smart city traffic signal management system

    ZHANG FENG | Europäisches Patentamt | 2023

    Freier Zugriff

    Smart City Solutions for Traffic Management

    Niranjan, Maitreya / Nachiketh, K. S. / Kashyap, Naman et al. | Springer Verlag | 2025


    SMART CITY TRAFFIC INFORMATION MANAGEMENT SYSTEM

    KIM MYUNG SUP | Europäisches Patentamt | 2023

    Freier Zugriff