We propose a new method, video repairing, to robustly infer missing static background and moving foreground due to severe damage or occlusion from a video. To recover background pixels, we extend the image repairing method, where layer segmentation and homography blending are used to preserve temporal coherence and avoid flickering. By exploiting the constraint imposed by periodic motion and a subclass of camera and object motions, we adopt a two-phase approach to repair moving foreground pixels: In the sampling phase, motion data are sampled and regularized by 3D tensor voting to maintain temporal coherence and motion periodicity. In the alignment phase, missing moving foreground pixels are inferred by spatial and temporal alignment of the sampled motion data at multiple scales. We experimented our system with some difficult examples, where the camera can be stationary or in motion.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Video repairing: inference of foreground and background under severe occlusion


    Contributors:
    Jiaya Jia, (author) / Tai-Pang, W. (author) / Yu-Wing Tai, (author) / Chi-Keung Tang, (author)


    Publication date :

    2004-01-01


    Size :

    1044463 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Video Repairing: Inference of Foreground and Background under Severe Occlusion

    Jia, J. / Wu, T.-P. / Tai, Y.-W. et al. | British Library Conference Proceedings | 2004


    Smooth Foreground-Background Segmentation for Video Processing

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


    Two video analysis applications using foreground/background segmentation

    Zivkovic, Z. / Petkovic, M. / van Mierlo, R. et al. | British Library Conference Proceedings | 2003