A unified mixture framework for motion segmentation: incorporating spatial coherence and estimating the number of models
- 1 January 1996
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 321-326
- https://doi.org/10.1109/cvpr.1996.517092
Abstract
Describing a video sequence in terms of a small number of coherently moving segments is useful for tasks ranging from video compression to event perception. A promising approach is to view the motion segmentation problem in a mixture estimation framework. However, existing formulations generally use only the motion, data and thus fail to make use of static cues when segmenting the sequence. Furthermore, the number of models is either specified in advance or estimated outside the mixture model framework. In this work we address both of these issues. We show how to add spatial constraints to the mixture formulations and present a variant of the EM algorithm that males use of both the form and the motion constraints. Moreover this algorithm estimates the number of segments given knowledge about the level of model failure expected in the sequence. The algorithm's performance is illustrated on synthetic and real image sequences.Keywords
This publication has 12 references indexed in Scilit:
- Image sequence enhancement using multiple motions analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Mixture models for optical flow computationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Detection of multiple moving objects using multiscale MRF with camera motion compensationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Probability distributions of optical flowPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Robust estimation of a multi-layered motion representationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Maximum-likelihood parameter estimation for unsupervised stochastic model-based image segmentationIEEE Transactions on Image Processing, 1994
- Statistical Physics, Mixtures of Distributions, and the EM AlgorithmNeural Computation, 1994
- Representing moving images with layersIEEE Transactions on Image Processing, 1994
- Parallel and deterministic algorithms from MRFs: surface reconstructionIeee Transactions On Pattern Analysis and Machine Intelligence, 1991
- Statistical mechanics and phase transitions in clusteringPhysical Review Letters, 1990