A methodology is developed to extract vehicle kinematic information from roadside cameras at an intersection using deep learning. The ground truth data of top view bounding boxes are collected with the help of unmanned aerial vehicles (UAVs). These top view bounding boxes containing vehicle position, size, and orientation information, are converted to the roadside view bounding boxes using homography transformation. The ground truth data and the roadside view images are used to train a modified YOLOv5 neural network, and thus, to learn the homography transformation matrix. The output of the neural network is the vehicle kinematic information, and it can be visualized in both the top view and the roadside view. In our algorithm, the top view images are only used in training, and once the neural network is trained, only the roadside cameras are needed to extract the kinematic information.


    Access

    Download


    Export, share and cite



    Title :

    YOLOgraphy: Image Processing Based Vehicle Position Recognition


    Additional title:

    Lect.Notes Mechanical Engineering



    Conference:

    Advanced Vehicle Control Symposium ; 2024 ; Milan, Italy September 01, 2024 - September 05, 2024



    Publication date :

    2024-10-04


    Size :

    7 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English





    Image Processing based Vehicle Number Plate Recognition

    Kamble, K.P. / Chaudhary, Kalyani / Admane, Rachana et al. | IEEE | 2022


    OWN VEHICLE POSITION RECOGNITION DEVICE AND OWN VEHICLE POSITION RECOGNITION METHOD

    YOU BYUNG YONG / HEO MYUNG SEON / WU YEONG CHUL | European Patent Office | 2016

    Free access

    POSITION RECOGNITION METHOD AND POSITION RECOGNITION SYSTEM FOR VEHICLE

    LEE HUN / SHIN DONG HYUK / KIM KI JAE et al. | European Patent Office | 2024

    Free access

    VEHICLE POSITION RECOGNITION DEVICE

    MORI NAOKI | European Patent Office | 2022

    Free access

    POSITION RECOGNITION METHOD AND POSITION RECOGNITION SYSTEM FOR VEHICLE

    KIM SEO HYUN / LEE HUN / SHIN DONG HYUK et al. | European Patent Office | 2022

    Free access