For effective city planning and traffic control, it is now crucial to develop some effective monitoring systems for vehicle traffic in order to address this quickly growing tendency within a city. As a result, the TrackNCount project combines DeepSORT with YOLOv8 for object identification to create a smart system for tracking, counting, and speed estimation of vehicles. The idea behind this design is to use sophisticated computer vision techniques in conjunction with efficient algorithms to handle real-world scenarios. Setting up a reliable procedure that recognizes cars, gives them distinct IDs, and records their movements through video frames is our first priority. The system computes vehicle speeds using the Euclidean distance formula, manages item trajectories using double-ended queues, and detects entering and outgoing vehicles based on directional thresholds. Motion trails and bounding boxes are two further visual aids that improve the results' readability. With the added benefit of simple speed estimation feature integration, the model provides exceptional accuracy in real-time vehicle monitoring and counting. Experiments conducted on a variety of traffic scenarios consistently showed that this system can deliver precise vehicle counts in designated directions and speed calculations with a small margin of error. The findings show that TrackNCount is a viable and scalable solution for data-driven city planning and intelligent traffic management.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    TrackNCount - Intelligent Vehicle Tracking, Counting, and Speed Estimation Using YOLOv8 and DeepSORT Algorithms




    Publication date :

    2025-01-07


    Size :

    611374 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Research on Improved YOLO and DeepSORT Ship Detection and Tracking Algorithms

    Qi, Bohan / Zhang, Pei / Huang, Wenbin | IEEE | 2024


    YOLOv8 for Vehicle Detection and Speed Estimation

    Do, Anh Kim Thi / Le Truong, Thanh My / Debnath, Narayan C. et al. | Springer Verlag | 2025


    Real-Time Speed Estimation of Moving Vehicle Using YOLOv8

    Sachdeva, Kashish / Singh, Vivek Kumar / Suryakant et al. | IEEE | 2024


    Enhancing Real-Time Human Tracking using YOLONAS-DeepSort Fusion Models

    Athilakshmi, R. / Chandan Sainagakrishna, Pulavarthi Sri / Chaitanya Chowdary Kota, S. Sri et al. | IEEE | 2023