Mixed-State Auto-Models and Motion Texture Modeling

Bouthémy, Patrick; Hardouin, Cécile; Piriou, Gwénaëlle; Yao, Jianfeng

doi:10.1007/s10851-006-7251-1

Cited by 31 publications

(45 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the video primal sketch model, I Λ 0 may be modeled either by the sparse coding model in (5) or by the FRAME model in (11). The choice is determined via the competition between the two models, i.e., comparing which model gives shorter coding length [33] for representation.…”

Section: Sketchability and Trackability For Model Selectionmentioning

confidence: 99%

Video Primal Sketch: A Unified Middle-Level Representation for Video

2015

View full text Add to dashboard Cite

This paper presents a middle-level video representation named video primal sketch (VPS), which integrates two regimes of models: (i) sparse coding model using static or moving primitives to explicitly represent moving corners, lines, feature points, etc., (ii) FRAME /MRF model reproducing feature statistics extracted from input video to implicitly represent textured motion, such as water and fire. The feature statistics include histograms of spatio-temporal filters and velocity distributions. This paper makes three contributions to the literature: (i) Learning a dictionary of video primitives using parametric generative models; (ii) Proposing the spatio-temporal FRAME and motion-appearance FRAME models for modeling and synthesizing textured motion; and (iii) Developing a parsimonious hybrid model for generic video representation. Given an input video, VPS selects the proper models automatically for different motion patterns and is compatible with high-level action representations. In the experiments, we synthesize a number of textured motion; reconstruct real videos using the VPS; report a series of human perception experiments to verify the quality of reconstructed videos; demonstrate how the VPS changes over the

show abstract

Section: Sketchability and Trackability For Model Selectionmentioning

confidence: 99%

Video Primal Sketch: A Unified Middle-Level Representation for Video

2015

View full text Add to dashboard Cite

show abstract

“…It should be emphasized that this kind of a mask is meaningful only when the camera is static, or camera motion has been compensated for. Thus, in the most general case, it should be derived from the residual motion vectors (the motion measurements remaining after camera motion compensation), as in [17].…”

Section: Kurtosis-based Activity Areamentioning

confidence: 99%

Robust Temporal Activity Templates Using Higher Order Statistics

Briassouli

Kompatsiaris

2009

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

A robust, theoretically-founded approach for the extraction of temporal templates corresponding to areas of motion in video, is presented. Higher order statistics (kurtosis) are employed to extract Activity Areas, i.e. binary masks indicating which pixels in a video are active. The application of the kurtosis on illumination changes modeled as Gaussians and Mixture of Gaussians is shown to be sensitive to outliers for both models, thus correctly localizing active pixels. Activity Areas are compared to existing, difference-based temporal templates, known as Motion Energy Images, and the robustness of both categories of temporal templates to additive noise is analyzed theoretically. Experiments with numerous real videos with additive noise, both indoors and outdoors, are conducted to compare the robustness of the Activity Areas and Motion Energy Images, and their temporal extensions, the Activity History Areas and Motion History Images. As expected from the theoretical analysis, the kurtosis-based Activity Areas prove to be more robust than the difference-based templates. Challenging videos containing occlusions, varying backgrounds and shadows are also examined, and it is shown that the proposed approach outperforms the difference-based method for these cases as well, consistently providing reliable localization of activity under a wide range of difficult circumstances. The proposed approach provides good results at a very low computational cost, and without requiring prior knowledge about the scene, nor training of any kind.

show abstract

“…CRF models until now were developed for either continuous or discrete random variables [6,5]. Conversely, inspired from [9], we are here interested in modelling a energy functional E(x, y), over y ∈ S N , where S is a mixed space defined by S = Ω ∪ R, with R the space of reals and Ω the space of symbolic concepts. The notion of "mixed-state" comes then from the bi-modal nature of the unknown y, either continuous (in R), either symbolic (ω ∈ Ω).…”

Section: Definitions and Fundamentals On Mixed-state Conditional Randmentioning

confidence: 99%

“…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 Auto-Models and Motion Texture Modeling

Cited by 31 publications

References 12 publications

Video Primal Sketch: A Unified Middle-Level Representation for Video

Video Primal Sketch: A Unified Middle-Level Representation for Video

Robust Temporal Activity Templates Using Higher Order Statistics

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

Contact Info

Product

Resources

About