Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOI: 10.1109/cvpr.1992.223240
|View full text |Cite
|
Sign up to set email alerts
|

A MRF approach to optical flow estimation

Abstract: 4 frameatt Imaging Department Siemens Corporate Research, Inc Princeton, N J 08540 W e studied a Markov random field ( M R F ) formubat i o n f o r the problem of optical flow computation. W e first consider a n adaptive window matching scheme t o obtain a good measure of the correlation between the t w o images. W e also considered a confidence measure f o r each match. Thus, the input t o our system is a n adaptive correlation and the corresponding confidence. W e t h e n use the M R F model t o estimate the… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0
8

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 10 publications
(13 citation statements)
references
References 4 publications
0
5
0
8
Order By: Relevance
“…The modeling step is reduced to the definition of a global energy function U. It can be decomposed into a sum of several potential functions: U=Vc (3) ceC C represents the set of cliques c associated with the chosen neighborhood (Fig. 1), and the MAP criterion (1) consists in minimizing the global function energy (4) .…”
Section: X=(ew)mentioning
confidence: 99%
See 1 more Smart Citation
“…The modeling step is reduced to the definition of a global energy function U. It can be decomposed into a sum of several potential functions: U=Vc (3) ceC C represents the set of cliques c associated with the chosen neighborhood (Fig. 1), and the MAP criterion (1) consists in minimizing the global function energy (4) .…”
Section: X=(ew)mentioning
confidence: 99%
“…It determines which values of the observation are considered as outliers >>.The working up of this estimator is equivalent to an iterative weighted least squares method with the the first stage of the algorithm, when the parameters are not estimated yet, the parameters w, are all taken equal to 1 . With the new values of the o are calculated using the equation(3). The process alternates between estimating o and f until convergence.…”
mentioning
confidence: 99%
“…A significant amount of work has been done to solve correspondence problem and most of the work can be classified into two categories: feature-based matching [2] [3] and area-based matching [4] [5] . Feature-based stereo techniques use symbolic features derived from intensity images rather than image intensities themselves, hence feature extractions are required in the preprocessing stage.…”
Section: Introductionmentioning
confidence: 99%
“…For instance, in [20,49] Markov random field (MRF) models are proposed along with a maximum a-posteriori criterion for estimating optical flow. MRF models are also used in [18] to address problems of occlusion and flow field discontinuity.…”
Section: An Estimation-theoretic Interpretation Of the Optical Flow Pmentioning
confidence: 99%