The accelerated advancement of urban infrastructure has underscored the significance of smart city technologies, especially within traffic management, wherein vehicle detection and classification assume a crucial role. This manuscript presents a vehicle identification framework specifically designed for the roadways of Bangladesh, employing the YOLOv8n model to optimize traffic flow, alleviate congestion, and augment road safety. The system utilizes a custom dataset from real-time traffic footage in Bangladesh, classifying vehicles into eight categories. As part of this study, we evaluated our model utilizing Bangladeshi real-time traffic video data. The study showcases the model's capability to navigate intricate urban settings, although accuracy enhancement is necessary, especially in congested traffic. The findings underscore the model's potential for improving traffic surveillance and supporting smart city developments.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Vehicle Classification and Detection Using YOLOv8: A Study on Highway Traffic Analysis


    Beteiligte:


    Erscheinungsdatum :

    07.12.2024


    Format / Umfang :

    792303 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Traffic Sign Detection Using YOLOv8

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


    Real-time traffic accident detection using yolov8

    Huy Minh, Quang Nguyen / Dinh, Nen Nguyen / Ho, Long Viet et al. | Elsevier | 2025

    Freier Zugriff

    Comparative Analysis Yolov5 and Yolov8 for Vehicle Classification

    Jain, Muskan / Sharma, Ranjana | IEEE | 2024


    Analysis of Traffic Management System using YOLOv8

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


    Proactive Highway Collision Avoidance using YOLOv8 and Ultrasonic Sensors

    Kavitha, M. / Akshaya, A. / Jotheeswaran, K. et al. | IEEE | 2024