The concept of automated incident detection is based on the idea of finding suitable image cues that can represent the specific event of interest with minimum overlapping with other classes. In this paper motion is adopted as the main cue for abnormal incident detection. First, scene motion information is extracted by a hardware implemented exhaustive block matching motion detector, followed by a stage of motion segmentation and filtering. The extracted motion information from sequences with normal events is fed to a neural network as training data. Hence, the system is first set to learn the usual motion patterns in the scene as a means of detecting abnormal motion patterns as they arise. Some of the previous work in this field is presented. The neural network model, the run-time techniques employed to detect the abnormal agents and a typical example of implementation, are described.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Image processing system for pedestrian monitoring using neural classification of normal motion patterns


    Contributors:

    Published in:

    Measurement and Control ; 32 , 9 ; 261-264


    Publication date :

    1999


    Size :

    4 Seiten, 11 Quellen



    Type of media :

    Article (Journal)


    Type of material :

    Print


    Language :

    English




    Pedestrian Detection Using Global-Local Motion Patterns

    Goel, Dhiraj / Chen, Tsuhan | Springer Verlag | 2007


    Image Monitoring Motorway: Pedestrian Detection Using Image Processing

    Bouzar, S. / Glachet, R. / Biosseville, J. M. et al. | British Library Conference Proceedings | 1996


    Pedestrian classification from moving platforms using cyclic motion pattern

    Yang Ran, / Qinfen Zheng, / Weiss, I. et al. | IEEE | 2005


    Pedestrian Classification from Moving Platforms using Cyclic Motion Pattern

    Ran, Y. / Zheng, Q. / Weiss, I. et al. | British Library Conference Proceedings | 2005