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.
Learning flexible sprites in video layers
2001-01-01
1016561 byte
Conference paper
Electronic Resource
English
Learning Flexible Sprites in Video Layers
British Library Conference Proceedings | 2001
|Interactive montages of sprites for indexing and summarizing security video
IEEE | 2005
|EM Radiation Associated with Sprites?
British Library Conference Proceedings | 1999
|Parameterization of Sprites and Their Parent Discharges
British Library Conference Proceedings | 1999
|