Abstract The detection of approaching vehicles in traffic lanes is an essential processing step for a driver assistant or a visual traffic monitoring system. For this task a new motion based approach is presented, which allows processing in real-time without the need of special hardware. Motion estimation was processed along contours and restricted to the observed lane(s). Due to the lane based computation vehicles were segmented by evaluation of the motion direction only. The contour tracking algorithm allows a robust motion estimation and a temporal stabilisation of the motion based segmentation. The capabilities of our approach are demonstrated in two applications: a overtake checker for highways and a visual traffic monitoring system.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Real-Time Motion Based Vehicle Segmentation in Traffic Lanes


    Contributors:

    Published in:

    Pattern Recognition ; 8 ; 202-207


    Publication date :

    2001-01-01


    Size :

    6 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English






    Managed Lanes-Traffic Modeling

    S. Vengluar / D. Fenno / S. Goel et al. | NTIS | 2002


    Quantifying the Mobility Benefits of Express Lanes using Real-Time Traffic Data

    Kadeha, Cecilia / Alluri, Priyanka / Sando, Thobias | Transportation Research Record | 2020