Abstract This paper presents a probabilistic approach for automatically segmenting foreground objects from a video sequence. In order to save computation time and be robust to noise effect, a region detection algorithm incorporating edge information is first proposed to identify the regions of interest. Next, we consider the motion of the foreground objects, and hence utilize the temporal coherence property on the regions detected. Thus, foreground segmentation problem is formulated as follows. Given two consecutive image frames and the segmentation result obtained priorly, we simultaneously estimate the motion vector field and the foreground segmentation mask in a mutually supporting manner. To represent the conditional joint probability density function in a compact form, a Bayesian network is adopted, which is derived to model the interdependency of these two elements. Experimental results for several video sequences are provided to demonstrate the effectiveness of our proposed approach.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Background Foreground Segmentation for SLAM

    Corcoran, P. / Winstanley, A. / Mooney, P. et al. | IEEE | 2011


    Flexible background mixture models for foreground segmentation

    Cheng, J. / Yang, J. / Zhou, Y. et al. | British Library Online Contents | 2006


    A spatially distributed model for foreground segmentation

    Dickinson, P. / Hunter, A. / Appiah, K. | British Library Online Contents | 2009


    Smooth Foreground-Background Segmentation for Video Processing

    Schindler, K. / Wang, H. | British Library Conference Proceedings | 2006


    Cross-Scale Guidance Network for Few-Shot Moving Foreground Object Segmentation

    Liao, Yi-Sheng / Lin, Yen-Wei / Chang, Ya-Han et al. | IEEE | 2025