Higher-order Autoregressive Models for Dynamic Textures

Dynamic textured sequences are characterized by the interactions between many particles or objects in the scene. Based on earlier work the images of the sequence are interpreted as the output of a linear autoregressive process driven by white Gaussian noise. We extend earlier work by increasing the amount temporal information included when learning the motion in the scene, allowing the models to capture complex motion patterns which extend over multiple frames, thereby increasing the perceptual accuracy of the synthesized results. To overcome problems of dynamic model stability, we apply Burg’s Maximum Entropy Spectral Analysis technique f or parameter estimation, which is found to be reliably stable on smaller samples of training data, even with higher-order dynamics.

[1]  Béla Julesz,et al.  Visual Pattern Discrimination , 1962, IRE Trans. Inf. Theory.

[2]  J. P. Burg,et al.  Maximum entropy spectral analysis. , 1967 .

[3]  B. Dickinson,et al.  Efficient solution of covariance equations for linear prediction , 1977 .

[4]  O. Strand.  Multichannel complex maximum entropy (autoregressive) spectral analysis , 1977 .

[5]  M. Kaveh,et al.  An optimum tapered Burg algorithm for linear prediction and spectral analysis , 1983 .

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

[7]  Bart De Moor,et al.  N4SID: Subspace algorithms for the identification of combined deterministic-stochastic systems , 1994, Autom..

[8]  James R. Bergen,et al.  Pyramid-based texture analysis/synthesis , 1995, Proceedings., International Conference on Image Processing.

[9]  J. Bergen,et al.  Pyramid-based texture analysis/synthesis , 1995, Proceedings., International Conference on Image Processing.

[10]  Martin Szummer,et al.  Temporal texture modeling , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[11]  Jeremy S. De Bonet,et al.  Multiresolution sampling procedure for analysis and synthesis of texture images , 1997, SIGGRAPH.

[12]  Alexei A. Efros,et al.  Texture synthesis by non-parametric sampling , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[13]  Richard Szeliski,et al.  Video textures , 2000, SIGGRAPH.

[14]  Baining Guo,et al.  Chaos Mosaic: Fast and Memory Efficient Texture Synthesis , 2000 .

[15]  A. Robinson.  A Comparison Between The Em And Subspace Identification Algorithms For Time-Invariant Linear Dynamic , 2000 .

[16]  Marc Levoy,et al.  Fast texture synthesis using tree-structured vector quantization , 2000, SIGGRAPH.

[17]  Payam Saisan,et al.  Dynamic texture recognition , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[18]  Dani Lischinski,et al.  Texture Mixing and Texture Movie Synthesis Using Statistical Learning , 2001, IEEE Trans. Vis. Comput. Graph..

[19]  Alexei A. Efros,et al.  Image quilting for texture synthesis and transfer , 2001, SIGGRAPH.

[20]  Baining Guo,et al.  Real-time texture synthesis by patch-based sampling , 2001, TOGS.

[21]  Stefano Soatto,et al.  Editable dynamic textures , 2002, SIGGRAPH '02.

[22]  Irfan A. Essa,et al.  Graphcut textures: image and video synthesis using graph cuts , 2003, ACM Trans. Graph..

[23]  Eero P. Simoncelli,et al.  A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients , 2000, International Journal of Computer Vision.

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

[25]  Nuno Vasconcelos,et al.  Probabilistic kernels for the classification of auto-regressive visual processes , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).