Robust Optical Flow Computation Based on Least-Median-of-Squares Regression
International Journal of Computer Vision
On Active Camera Control and Camera Motion Recovery with Foveate Wavelet Transform
IEEE Transactions on Pattern Analysis and Machine Intelligence
Estimation of Occlusion and Dense Motion Fields in a Bidirectional Bayesian Framework
IEEE Transactions on Pattern Analysis and Machine Intelligence
MAP-Based Stochastic Diffusion for Stereo Matching and Line Fields Estimation
International Journal of Computer Vision
Hidden Markov Measure Field Models for Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
MRF-MAP-MFT visual object segmentation based on motion boundary field
Pattern Recognition Letters
An application of MAP-MRF to change detection in image sequence based on mean field theory
EURASIP Journal on Applied Signal Processing
Stereo image coder based on the MRF model for disparity compensation
EURASIP Journal on Applied Signal Processing
Optimization by Stochastic Continuation
SIAM Journal on Imaging Sciences
Hi-index | 0.01 |
Previously, Markov random field (MRF) model-based techniques have been proposed for image motion estimation. Since motion estimation is usually an ill-posed problem, various constraints are needed to obtain a unique and stable solution. The main advantage of the MRF approach is its capacity to incorporate such constraints, for instance, motion continuity within an object and motion discontinuity at the boundaries between objects. In the MRF approach, motion estimation is often formulated as an optimization problem, and two frequently used optimization methods are simulated annealing (SA) and iterative-conditional mode (ICM). Although the SA is theoretically optimal in the sense of finding the global optimum, it usually takes many iterations to converge. The ICM, on the other hand, converges quickly, but its results are often unsatisfactory due to its “hard decision” nature. Previously, the authors have applied the mean field theory to image segmentation and image restoration problems. It provides results nearly as good as SA but with much faster convergence. The present paper shows how the mean field theory can be applied to MRF model-based motion estimation. This approach is demonstrated on both synthetic and real-world images, where it produced good motion estimates