Mixed-state causal modeling for statistical KL-based motion texture tracking

We are interested in the modeling and tracking of dynamic or motion textures, which refer to dynamic contents that can be classified as a texture with motion (fire, smoke, crowd of people). Experimentally we observe that they depict motion maps with values of a mixed type: a discrete value at zero (absence of motion) and continuous non-null motion values. We thus introduce a temporal mixed-state Markov model for the characterization of motion textures from which a set of 13 parameters is extracted as the descriptive feature of the dynamic content. Then, a motion texture tracking strategy is proposed using the conditional Kullback-Leibler (KL) divergence between mixed-state probability densities, which allows us to estimate the position using a statistical matching approach.

[1]  Patrick Bouthemy,et al.  Mixed-State Markov Random Fields for Motion Texture Modeling and Segmentation , 2006, 2006 International Conference on Image Processing.

[2]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[3]  René Vidal,et al.  Optical flow estimation & segmentation of multiple moving dynamic textures , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Patrick Bouthemy,et al.  Mixed-State Auto-Models and Motion Texture Modeling , 2006, Journal of Mathematical Imaging and Vision.

[5]  Patrick Pérez,et al.  Color-Based Probabilistic Tracking , 2002, ECCV.

[6]  Patrick Bouthemy,et al.  Simultaneous Motion Detection and Background Reconstruction with a Mixed-State Conditional Markov Random Field , 2008, ECCV.

[7]  Kai-Kuang Ma,et al.  A new diamond search algorithm for fast block-matching motion estimation , 2000, IEEE Trans. Image Process..

[8]  Randal C. Nelson,et al.  Qualitative recognition of motion using temporal texture , 1992, CVGIP Image Underst..

[9]  Nuno Vasconcelos,et al.  Layered Dynamic Textures , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Patrick Pérez,et al.  Nonparametric motion characterization using causal probabilistic models for video indexing and retrieval , 2002, IEEE Trans. Image Process..

[11]  Sándor Fazekas.  Normal versus complete flow in dynamic texture recognition: a comparative study , 2005 .

[12]  Christophe Collet,et al.  Fuzzy Markov Random Fields versus Chains for Multispectral Image Segmentation , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Donald Geman,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[14]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[15]  Bing Zeng,et al.  A new three-step search algorithm for block motion estimation , 1994, IEEE Trans. Circuits Syst. Video Technol..

[16]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[17]  B. Anderson,et al.  Optimal Filtering , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[18]  Jianhua Lu,et al.  A simple and efficient search algorithm for block-matching motion estimation , 1997, IEEE Trans. Circuits Syst. Video Technol..

[19]  Stefano Soatto,et al.  Dynamic Textures , 2003, International Journal of Computer Vision.

[20]  Dmitry Chetverikov,et al.  Dynamic Texture Detection Based on Motion Analysis , 2009, International Journal of Computer Vision.