The mean field theory for image motion estimation

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.<<ETX>>

[1]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  J. Besag.  On the Statistical Analysis of Dirty Pictures , 1986 .

[3]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[4]  D. Chandler,et al.  Introduction To Modern Statistical Mechanics , 1987 .

[5]  M. Bertero,et al.  Ill-posed problems in early vision , 1988, Proc. IEEE.

[6]  Jan Biemond,et al.  A pel-recursive segmentation and estimation algorithm for motion compensated image sequence coding , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[7]  Eric Dubois,et al.  Comparison of stochastic and deterministic solution methods in Bayesian estimation of 2D motion , 1990, Image Vis. Comput..

[8]  Federico Girosi,et al.  Parallel and deterministic algorithms from MRFs: surface reconstruction and integration , 1990, ECCV.

[9]  P. Pérez,et al.  Parallel visual motion analysis using multiscale Markov random fields , 1991, Proceedings of the IEEE Workshop on Visual Motion.

[10]  Wesley E. Snyder,et al.  Energy minimization approach to motion estimation , 1992, Signal Process..

[11]  Jun Zhang,et al.  Maximum-likelihood parameter estimation for unsupervised stochastic model-based image segmentation , 1994, IEEE Trans. Image Process..

[12]  Jun Zhang,et al.  The application of mean field theory to image motion estimation , 1995, IEEE Trans. Image Process..