We propose a technique for automatically learning layers of "flexible sprites" (probabilistic 2-dimensional appearance maps and masks of moving, occluding objects). The model explains each input image as a layered composition of flexible sprites. A variational expectation maximization algorithm is used to learn a mixture of sprites from a video sequence. For each input image, probabilistic inference is used to infer the sprite class, translation, mask values and pixel intensities (including obstructed pixels) in each layer. Exact inference is intractable, but we show how a variational inference technique can be used to process 320/spl times/240 images at 1 frame/second. The only inputs to the learning algorithm are the video sequence, the number of layers and the number of flexible sprites. We give results on several tasks, including summarizing a video sequence with sprites, point-and-click video stabilization, and point-and-click object removal.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning flexible sprites in video layers


    Contributors:
    Jojic, N. (author) / Frey, B.J. (author)


    Publication date :

    2001-01-01


    Size :

    1016561 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Learning Flexible Sprites in Video Layers

    Jojic, N. / Frey, B. J. / IEEE | British Library Conference Proceedings | 2001



    EM Radiation Associated with Sprites?

    Otsuyama, T. / Hobara, Y. / Hayakawa, M. et al. | British Library Conference Proceedings | 1999


    Parameterization of Sprites and Their Parent Discharges

    Stanley, M. / Krehbiel, P. / Brook, M. et al. | British Library Conference Proceedings | 1999