Traffic congestions and traffic jams are major challenges in some cities due to the substantial surge in the population and the number of cars. Thus, controlling the traffic density on roads and highways is essential. In this paper, we explore a method that can be used to direct traffic. This method is based on image processing and comparing two images with and without cars. At first, the foreground of the image is obtained. Then the road is partitioned to calculate the area occupied by a car in each part of the road. After that, the number of cars is estimated through dividing the total area of cars by that of a typical car. The camera angle and road distance from the camera are two essential factors in this method. Therefore, it is vital to use a fixed camera in this method. This proposed model was tested with the GRAM-RTM dataset and exhibited an average accuracy of 95%.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Car Counting Based on Road Partitioning and Blobs Analysis


    Additional title:

    Lecture Notes on Data Engineering and Communications Technologies


    Contributors:


    Publication date :

    2022-09-02


    Size :

    8 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Active Blobs

    Sclaroff, S. / Isidoro, J. / IEEE; Computer Society | British Library Conference Proceedings | 1998


    Active blobs: region-based, deformable appearance models

    Sclaroff, S. / Isidoro, J. | British Library Online Contents | 2003


    Detection of Blobs Using Variable Windows

    Saitoh, M. / Katsulai, H. | British Library Online Contents | 1995


    A sparse curvature-based detector of affine invariant blobs

    Ferraz, L. / Binefa, X. | British Library Online Contents | 2012


    Real-time Human Figure Control Using Tracked Blobs

    Yonemoto, S. / Nakano, H. / Taniguchi, R. et al. | British Library Conference Proceedings | 2003