Mixed-State Markov Random Fields for Motion Texture Modeling and Segmentation

Crivelli, Tomas; Cernuschi-Frias, B.; Bouthémy, Patrick; Yao, Jianfeng

doi:10.1109/icip.2006.312842

Cited by 12 publications

(26 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…texture modeling and analysis, Lorette et al 2000, optical flow estimation, Heitz and Bouthemy 1993;Li and Huttenlocher 2008, image restoration and denoising, Chen and Tang 2007;Geman and Geman 1984) as well as decision problems (e.g. image segmentation, Collet and Murtagh 2004;Salzenstein and Collet 2006;Crivelli et al 2006;Benboudjema and Pieczynski 2007;Blanchet andForbes 2008, motion detection, Benedek et al 2007;Bouthemy and Lalande 1993, edge detection, Wu and Chung 2007, structural change detection, Kasetkasem and Varshney 2002. Our motivation have been to exploit the power of mixed-state MRF's for simultaneous decisionestimation problems.…”

Section: Mixed-state Auto-models With Symbolic Valuesmentioning

confidence: 99%

“…It is demonstrated that the normal flow scalar motion observations extracted from these video sequences, show a discrete value at zero (null-motion) and a Gaussian continuous distribution for the rest of the values. This model was extended in Crivelli et al (2006Crivelli et al ( , 2009 and applied to the problems of motion texture segmentation, recognition and tracking. For these applications, the issue is different than for simultaneous decisionestimation problems.…”

Section: Related Work and Connectionsmentioning

confidence: 99%

See 1 more Smart Citation

Simultaneous Motion Detection and Background Reconstruction with a Conditional Mixed-State Markov Random Field

et al. 2011

View full text Add to dashboard Cite

In this work we present a new way of simultaneously solving the problems of motion detection and background image reconstruction. An accurate estimation of the background is only possible if we locate the moving objects. Meanwhile, a correct motion detection is achieved if we have a good available background model. The key of our joint approach is to define a single random process that can take two types of values, instead of defining two different processes, one symbolic (motion detection) and one numeric (background intensity estimation). It thus allows to exploit the (spatio-temporal) interaction between a decision (motion detection) and an estimation (intensity reconstruction) problem. Consequently, the meaning of solving both tasks jointly, is to obtain a single optimal estimate of such a process. The intrinsic interaction and simultaneity between both problems is shown to be better modeled within the so-called mixed-state statistical framework, which is extended here to account for symbolic states and conditional random fields.T. Crivelli ( ) · B. Cernuschi-Frías Experiments on real sequences and comparisons with existing motion detection methods support our proposal. Further implications for video sequence inpainting will be also discussed.

show abstract

Section: Mixed-state Auto-models With Symbolic Valuesmentioning

confidence: 99%

Section: Related Work and Connectionsmentioning

confidence: 99%

Simultaneous Motion Detection and Background Reconstruction with a Conditional Mixed-State Markov Random Field

et al. 2011

View full text Add to dashboard Cite

show abstract

“…Other approaches are based on modeling motion features extracted from the image sequence instead of considering pixel-wise intensity values [3,5,8]. Particularly, normal flow is a very efficient and natural way of locally characterizing a dynamic texture [8].…”

Section: Related Workmentioning

confidence: 99%

“…In this work we are interested in the modeling and tracking of temporal textures, nowadays known as dynamic textures or motion textures [10,7,13,3,5]. Mostly, they refer to dynamic video contents displayed by natural scene elements as rivers, sea-waves, smoke, moving foliage, fire, etc.…”

mentioning

confidence: 99%

Learning mixed-state Markov models for statistical motion texture tracking

Crivelli¹,

Bouthémy

Cernuschi-Frias³

et al. 2009

2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops

Self Cite

View full text Add to dashboard Cite

A motion texture is the instantaneous scalar map of apparent motion values extracted from a dynamic or temporal texture. It is mostly displayed by natural scene elements (fire, smoke, water) but also involves more general textured motion patterns (eg. a crowd of people, a flock). In this work we are interested in the modeling and tracking of motion textures. Experimentally we observe that such motion maps exhibit values of a mixed type: a discrete component at zero and a continuous component of non-null motion values. Thus, we propose a statistical characterization of motion textures based on a mixed-state causal modeling. Next, the problem of tracking is considered. A set of mixedstate model parameters is learned as a descriptive feature of the motion texture to track and displacement estimation is solved using the conditional Kullback-Leibler divergence for statistical window matching. Results and comparisons are presented on real sequences.

show abstract

“…The mixed state nature of the random variable compels us to define properly a density function that is associated to it (see [9,10]). Let us first define, for a given element y i , a mixed measure : m(dy i ) = δ ω (dy i ) + λ(dy i ) where δ ω is the Dirac measure at ω ∈ Ω and λ the Lebesgue measure over R. We note δ * ω = 1− δ ω (y i ).…”

Section: Definitions and Fundamentals On Mixed-state Conditional Randmentioning

confidence: 99%

Conditional mixed-state model for structural change analysis from very high resolution optical images

Belmudez

Prinet

Yao

et al. 2009

2009 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

The present work concerns the analysis of dynamic scenes from earth observation images. We are interested in building a map which, on one hand locates places of change, on the other hand, reconstructs a unique visual information of the non-change areas. We show in this paper that such a problem can naturally be takled with conditional mixed-state random field modeling (mixed-state CRF), where the "mixed state" refers to the symbolic or continous nature of the unknown variable. The maximum a posteriori (MAP) estimation of the CRF is, through the Hammersley-Clifford theorem, turned into an energy minimisation problem. We tested the model on several Quickbird images and illustrate the quality of the results.

show abstract

Mixed-State Markov Random Fields for Motion Texture Modeling and Segmentation

Cited by 12 publications

References 6 publications

Simultaneous Motion Detection and Background Reconstruction with a Conditional Mixed-State Markov Random Field

Simultaneous Motion Detection and Background Reconstruction with a Conditional Mixed-State Markov Random Field

Learning mixed-state Markov models for statistical motion texture tracking

Conditional mixed-state model for structural change analysis from very high resolution optical images

Contact Info

Product

Resources

About