A robust traffic surveillance system is one of the emerging fields in the existing system; the traffic surveillance system mainly concentrates on vehicular movement for effective management of traffic. Vehicle flow detection plays a prominent role in the surveillance system. The main drawback of the existing system is it consumes more time and results in false detection due to the presence of the shadow. Hence, in this paper, mixture of Gaussian (MoG2) model is proposed to extract the foreground from the background efficiently, followed by Gaussian blur and morphological operation for efficient shadow removal. Finally, dynamic object detection is using blob detection where the vehicle is shown as a rectangular patch from which meaningful features are extracted and identified as vehicle object through blob analysis. Finally, the detected vehicles are tracked through blob tracking and counted using multiple reference lines by measuring the minimal distance between extracted features in consecutive frames. The experimental results of the proposed system show a maximum efficiency of 91%.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Vision-Based Vehicle Detection and Tracking System


    Additional title:

    Lecture Notes on Data Engineering and Communications Technologies


    Contributors:

    Conference:

    Congress on Intelligent Systems ; 2020 ; New Delhi, India September 05, 2020 - September 06, 2020



    Publication date :

    2021-05-20


    Size :

    12 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Computer Vision-Based Vehicle Detection and Tracking

    Senthil Murugan, A. / Manoj Kumar, S. / Senthilrani, S. et al. | Springer Verlag | 2021




    Moving vehicle detection and tracking using monocular vision

    Miao,X. / Li,S. / Shen,H. et al. | Automotive engineering | 2014


    Moving vehicle detection and tracking using monocular vision

    Miao, Xiaoding / Li, Shunming / Shen, Huan et al. | Tema Archive | 2014