This paper describes a motion-analysis system, applied to the problem of vehicle tracking in real-world highway scenes. In the first stage, a motion-detection algorithm performs a figure/ground segmentation, providing binary masks of the moving objects. In the second stage, vehicles are tracked by using Kalman filters for two state vectors, which represent each target's position and velocity. Three types of features have been used: 1) the bounding rectangle, 2) the centroid of the convex polygon approximating the vehicles contour, and 3) the 2D pattern of the vehicle. For each feature, the performance of the tracking algorithm has been tested in terms of robustness and computing time.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Comparing features for target tracking in traffic scenes


    Additional title:

    Vergleich von Merkmalen zur Zielverfolgung in Verkehrsszenen


    Contributors:
    Gil, S. (author) / Milanese, R. (author) / Pun, T. (author)

    Published in:

    Pattern Recognition ; 29 , 8 ; 1285-1296


    Publication date :

    1996


    Size :

    12 Seiten, 19 Quellen




    Type of media :

    Article (Journal)


    Type of material :

    Print


    Language :

    English




    Towards Realtime Visual Based Tracking in Cluttered Traffic Scenes

    Koller, D. / Weber, J. / Malik, J. et al. | British Library Conference Proceedings | 1994


    Feature selection for object tracking in traffic scenes [2344-30]

    Gil, S. / Milanese, R. / Pun, T. et al. | British Library Conference Proceedings | 1995


    Monitoring crowded traffic scenes

    Maurin, B. / Masoud, O. / Papanikolopoulos, N. | IEEE | 2002


    MONITORING CROWDED TRAFFIC SCENES

    Maurin, B. / Masoud, O. / Papanikolopoulos, N. et al. | British Library Conference Proceedings | 2002