Learning layered motion segmentations of video
- 1 January 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 33-40 Vol. 1
- https://doi.org/10.1109/iccv.2005.138
Abstract
We present an unsupervised approach for learning a generative layered representation of a scene from a video for motion segmentation. The learnt model is a composition of layers, which consist of one or more segments. Included in the model are the effects of image projection, lighting, and motion blur. The two main contributions of our method are: (i) a novel algorithm for obtaining the initial estimate of the model using efficient loopy belief propagation; and (ii) using /spl alpha//spl beta/-swap and /spl alpha/-expansion algorithms, which guarantee a strong local minima, for refining the initial estimate. Results are presented on several classes of objects with different types of camera motion. We compare our method with the state of the art and demonstrate significant improvements.Keywords
This publication has 11 references indexed in Scilit:
- Learning flexible sprites in video layersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Greedy Learning of Multiple Objects in Images Using Robust Statistics and Factorial LearningNeural Computation, 2004
- Reconstructing Relief SurfacesPublished by British Machine Vision Association and Society for Pattern Recognition ,2004
- Variational space-time motion segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Learning the Statistics of People in Images and VideoInternational Journal of Computer Vision, 2003
- Using temporal coherence to build models of animalsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Fast approximate energy minimization via graph cutsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- An integrated Bayesian approach to layer extraction from image sequencesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Probabilistic Detection and Tracking of Motion BoundariesInternational Journal of Computer Vision, 2000
- Representing moving images with layersIEEE Transactions on Image Processing, 1994