A complex network approach for dynamic texture recognition

Abstract In this paper, we propose a novel approach for dynamic texture representation based on complex networks. In the proposed approach, each pixel of the video is mapped into a node of the complex network. Initially, a regular complex network is obtained by connecting two nodes if the Euclidean distance between their related pixels is equal or less than a given radius. For each connection, a weight is defined by the difference of the pixel intensities. Given the regular complex network, a function is applied to remove connections whose weight is equal to or below a given threshold. Finally, a feature vector is obtained by calculating the spatial and temporal average degree for networks transformed by different values of threshold and radius. The number of connections of pixels from the same frame and from different frames, respectively, gives the spatial and temporal degrees. Experimental results using synthetic and real dynamic textures have demonstrated the effectiveness of the proposed approach.

[1]  Li Li,et al.  A Survey on Visual Content-Based Video Indexing and Retrieval , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[2]  Dmitry Chetverikov,et al.  A Brief Survey of Dynamic Texture Description and Recognition , 2005, CORES.

[3]  A.B. Chan,et al.  Classification and retrieval of traffic video using auto-regressive stochastic processes , 2005, IEEE Proceedings. Intelligent Vehicles Symposium, 2005..

[4]  Matti Pietikäinen,et al.  Improving Rotation Invariance of the Volume Local Binary Pattern Operator , 2007, MVA.

[5]  Cordelia Schmid,et al.  Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[6]  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).

[7]  Nuno Vasconcelos,et al.  Modeling, Clustering, and Segmenting Video with Mixtures of Dynamic Textures , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Dmitry Chetverikov,et al.  Analysis and performance evaluation of optical flow features for dynamic texture recognition , 2007, Signal Process. Image Commun..

[9]  Sabine Süsstrunk,et al.  Higher Order SVD Analysis for Dynamic Texture Synthesis , 2008, IEEE Transactions on Image Processing.

[10]  André Ricardo Backes,et al.  Texture descriptor based on partially self-avoiding deterministic walker on networks , 2012, Expert Syst. Appl..

[11]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[12]  Randal C. Nelson,et al.  Recognition of motion from temporal texture , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Serge J. Belongie,et al.  Behavior recognition via sparse spatio-temporal features , 2005, 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance.

[14]  Ramprasad Polana,et al.  Temporal texture and activity recognition , 1994 .

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

[16]  Patrick Bouthemy,et al.  Motion Recognition Using Nonparametric Image Motion Models Estimated from Temporal and Multiscale Cooccurrence Statistics , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  S. Suzuki,et al.  Feature extraction of temporal texture based on spatiotemporal motion trajectory , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[18]  L. da F. Costa,et al.  Characterization of complex networks: A survey of measurements , 2005, cond-mat/0505185.

[19]  M. Omizo,et al.  Modeling , 1983, Encyclopedic Dictionary of Archaeology.

[20]  Odemir Martinez Bruno,et al.  A Rotation Invariant Face Recognition Method Based on Complex Network , 2010, CIARP.

[21]  Barbara Caputo,et al.  Class-Specific Material Categorisation , 2005, ICCV.

[22]  Daniel Cremers,et al.  Dynamic texture segmentation , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[23]  Michel Ménard,et al.  A Comparison of Wavelet Based Spatio-temporal Decomposition Methods for Dynamic Texture Recognition , 2009, IbPRIA.

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

[25]  Odemir Martinez Bruno,et al.  Dynamic texture analysis and segmentation using deterministic partially self-avoiding walks , 2013, Expert Syst. Appl..

[26]  M E J Newman,et al.  Community structure in social and biological networks , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[27]  Odemir Martinez Bruno,et al.  Complex network classification using partially self-avoiding deterministic walks , 2011, Chaos.

[28]  André Ricardo Backes,et al.  A complex network-based approach for boundary shape analysis , 2009, Pattern Recognit..

[29]  Duncan J. Watts,et al.  Collective dynamics of ‘small-world’ networks , 1998, Nature.

[30]  Albert,et al.  Emergence of scaling in random networks , 1999, Science.

[31]  Jianbo Shi,et al.  Detecting unusual activity in video , 2004, CVPR 2004.

[32]  Nuno Vasconcelos,et al.  Classifying Video with Kernel Dynamic Textures , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[33]  A. Barabasi,et al.  Network biology: understanding the cell's functional organization , 2004, Nature Reviews Genetics.

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

[35]  Narendra Ahuja,et al.  Maximum Margin Distance Learning for Dynamic Texture Recognition , 2010, ECCV.

[36]  M. Newman,et al.  Why social networks are different from other types of networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[37]  Richard P. Wildes,et al.  Classification of traffic video based on a spatiotemporal orientation analysis , 2011, 2011 IEEE Workshop on Applications of Computer Vision (WACV).

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

[39]  Matti Pietikäinen,et al.  Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.