A MRF approach to optical flow estimation

Vlontzos, J.A.; Geiger, Davi

doi:10.1109/cvpr.1992.223240

Cited by 10 publications

(13 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

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%

“…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%

See 1 more Smart Citation

<title>New method for segmentation and motion field estimation</title>

Bouchara

Richou

1996

SPIE Proceedings

View full text Add to dashboard Cite

In this paper we investigate a new approach to image sequence processing. In some applications of image processing (medical diagnosis, analysis of physical phenomena . . .) the segmented image and the motion field are both needed. It is physically coherent to suppose that these two kinds of data are linked together, and so it would be an improvement to take their mutual interaction into account : different areas make it possible to define motion boundaries and the motion field constitutes temporal information. This algorithm is based on the use of Markov Random Fields (M.R.F.) which yield good results in such domains. The use of MRF models in association with a Maximum A Posteriori (M.A.P.) criterion leads to the minimization of a hamiltonian which is a non-convex function in this case. In order to avoid local minima, we use a multigrid method to compute this minimum.

show abstract

Section: X=(ew)mentioning

confidence: 99%

mentioning

confidence: 99%

<title>New method for segmentation and motion field estimation</title>

Bouchara

Richou

1996

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…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%

<title>Solving correspondence problems with 1D signal matching</title>

2004

View full text Add to dashboard Cite

Signal matching can be applied to many applications, such as shape matching, stereo vision, image registration, and so on. With the development of hardware, 1D signal matching can be implemented with hardware to make fast processing more feasible. This is especially important for many real-time 3D vision applications such as unmanned air vehicles and mobile robots. When lighting variance is not significant in a controlled lighting environment or when the baseline is short, images taken from two viewpoints are quite similar. It is also true for each scan line pair if the attention is drawn to 1D signal. By processing 1D signal line by line, a dense disparity map can be achieved and 3D scene can be reconstructed. In this paper, we present a robust 1D signal matching method, which combines spline representation and genetic algorithm to obtain a dense disparity map. By imposing smoothness constraint implicitly, matching parameters can be solved in terms of their spline representations by minimizing a certain cost function. Genetic algorithm can then be used to perform the optimization task. Reconstruction results of three different scene settings are shown to prove the validity of our algorithm. Due to the similarity of the problem in nature, this algorithm can be easily extended to solve image registration and motion detection problems.

show abstract

“…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%

Efficient Multiscale Regularization with Applications to the Computation of Optical Flow

Luettgen¹,

Karl²,

Willsky³

1993

View full text Add to dashboard Cite

A new aplproach to regularization methods for image processing is iltro(duced and developed using as a. vehicle the problem of coml)uting dleilse optical flow fields in an image sequence. Standard formulations of this problemi re(luire the computationally intensive solution of an ellil)tic pa.rtial differential equation which arises froin the often used "smootlhness constraint' type regularization. We utilize the illterl)reta.tion of' .he smoot.hness constraint as a. "fractal prior" to motivate regularization based on a. recently introduced class of multiscale stochastic models. The solution of the new l)robleln formulat.ion is computed with an efficient multiscale algorithm. Experiiments on several ima.ge sequences (demonstrate the sutl)sta.nftial compult.a.tional savings tlia.t. canll I)e achieved due to the fact tha.t the algorit.hm is non-iterative and in fact has a. per pixel computational complexity which is independent. of imiage size. Tlie new a.pp)l)roach also has a. numbler of other important. advantages. Specifically, nitltiresolution flow field estimates are availabl)le, allowing grea.t. flexibility in dealing wvithl the t.radeoff b.)et.ween resolution a.nd(l accuracy. NIultiscale error covariance information is also availabLle. which is of considerable use inll assessing the accuracy of the estimates. Ini particular, these error statistics calln be used as the b)asis for a rational procedure for dletermlining the spatially-varying optimal reconstruction resolution. Furthermore, if there are conipelling reasons to insist upon a standard smoothness constraint, our algorithm provides an excellent initialization for the iterative algoritlhms associated with the smoot. ness constraint l)roblemi formulation. Finally, the usefulness of otir appI)roach should extend t-o a. wide variety of ill-posed inverse problems inll which variational techniques seeking a. "smooth" solution are generally usedl. EDICS category 1.11. Report Documentation PageForm Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden, to Washington Headquarters Services, Directorate for Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington VA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to a penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number.

show abstract

A MRF approach to optical flow estimation

Cited by 10 publications

References 4 publications

<title>New method for segmentation and motion field estimation</title>

<title>New method for segmentation and motion field estimation</title>

<title>Solving correspondence problems with 1D signal matching</title>

Efficient Multiscale Regularization with Applications to the Computation of Optical Flow

Contact Info

Product

Resources

About