Many video surveillance and identification applications need to find moving objects in the field of view of a stationary camera. A popular method for obtaining these silhouettes is through the process of background subtraction. We present a novel method for comparing image frames to the model of the stationary background that exploits the spatial and temporal dependencies that objects in motion impose on their images. We achieve this through the development and use of Markov random fields of binary segmentation variates. We show that the MRF approach produces more accurate and visually appealing silhouettes that are less prone to noise and background camouflaging effects than traditional per-pixel based methods. Results include visual examination of silhouettes, comparisons against hand-segmented data, and an analysis of the effects of various silhouette extraction techniques on gait recognition performance.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Background Subtraction Using Markov Thresholds


    Contributors:


    Publication date :

    2005-01-01


    Size :

    250968 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Background subtraction : theory and practice

    Elgammal, Ahmed | TIBKAT | 2015


    Fast Lighting Independent Background Subtraction

    Ivanov, Y. / Bobick, A. / Liu, J. | British Library Online Contents | 2000


    Smart Traffic Management System using Background Subtraction

    Kottha, Bharath Reddy / T, Anuradha / Penumacha, Naveen Kumar et al. | IEEE | 2024


    Background-Subtraction in Thermal Imagery Using Contour Saliency

    Davis, J. W. / Sharma, V. | British Library Online Contents | 2007