The mean field theory for image motion estimation
- 1 January 1993
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 5 (15206149) , 197-200 vol.5
- https://doi.org/10.1109/icassp.1993.319781
Abstract
It is shown how the MFT (mean field theory) can be applied to MRF (Markov random field) model-based motion estimation. Specifically, the motion is characterized by a coupled MRF including a displacement field (motion continuity), a line field (motion discontinuity), and a segmentation field (identifying uncovered areas). These fields are estimated by using the MFT. The efficacy of this approach is demonstrated on synthetic and real-world images.Keywords
This publication has 7 references indexed in Scilit:
- A pel-recursive segmentation and estimation algorithm for motion compensated image sequence codingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Parallel visual motion analysis using multiscale Markov random fieldsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The mean field theory for image motion estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Energy minimization approach to motion estimationSignal Processing, 1992
- Comparison of stochastic and deterministic solution methods in Bayesian estimation of 2D motionImage and Vision Computing, 1990
- Ill-posed problems in early visionProceedings of the IEEE, 1988
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1984