Block Motion Based Dynamic Texture Analysis: A Review

Dynamic texture refers to image sequences of non-rigid objects that exhibit some regularity in their movement. Videos of smoke, fire etc. fall under the category of dynamic texture. Researchers have investigated different ways to analyze dynamic textures since early nineties. Both appearance based (image intensities) and motion based approaches are investigated. Motion based approaches turn out to be more effective. A group of researchers have investigated ways to utilize the motion vectors readily available with the blocks in video codes like MGEG/H26X. In this paper we provide a review of the dynamic texture analysis methods using block motion. Research into dynamic texture analysis using block motion includes recognition, motion computation, segmentation, and synthesis. We provide a comprehensive review of these approaches.

[1]  Loong Fah Cheong,et al.  Synergizing spatial and temporal texture , 2002, IEEE Trans. Image Process..

[2]  Mohammad Manzur Murshed,et al.  Temporal Texture Characterization: A Review , 2008 .

[3]  M. Murshed,et al.  Segmentation of dynamic textures , 2007, 2007 10th international conference on computer and information technology.

[4]  A. Rahman,et al.  A Motion-Based Approach for Temporal Texture Synthesis , 2005, TENCON 2005 - 2005 IEEE Region 10 Conference.

[5]  Mark J. Huiskes,et al.  DynTex: A comprehensive database of dynamic textures , 2010, Pattern Recognit. Lett..

[6]  L.S. Dooley,et al.  A new video indexing and retrieval method for temporal textures using block-based cooccurrence statistics , 2004, 2004 International Networking and Communication Conference.

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

[8]  Ashfaqur Rahman,et al.  Detection of Multiple Dynamic Textures Using Feature Space Mapping , 2009, IEEE Transactions on Circuits and Systems for Video Technology.

[9]  A. Rahman,et al.  A feature based approach for multiple temporal texture detection , 2006, 2006 8th international Conference on Signal Processing.

[10]  Ashfaqur Rahman,et al.  A Temporal Texture Characterization Technique Using Block-Based Approximated Motion Measure , 2007, IEEE Transactions on Circuits and Systems for Video Technology.

[11]  Ashfaqur Rahman,et al.  A robust optical flow estimation algorithm for temporal textures , 2005, International Conference on Information Technology: Coding and Computing (ITCC'05) - Volume II.

[12]  Ashfaqur Rahman,et al.  Feature weighting methods for abstract features applicable to motion based video indexing , 2004, International Conference on Information Technology: Coding and Computing, 2004. Proceedings. ITCC 2004..

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

[15]  Ashfaqur Rahman,et al.  Feature Weighting and Retrieval Methods for Dynamic Texture Motion Features , 2009, Int. J. Comput. Intell. Syst..

[16]  L.S. Dooley,et al.  Temporal texture characterization for block-based video indexing , 2004, Proceedings. Elmar-2004. 46th International Symposium on Electronics in Marine.

[17]  Ashfaqur Rahman,et al.  Real-time temporal texture characterisation using block-based motion co-occurrence statistics , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[18]  Ashfaqur Rahman,et al.  Dynamic Texture Synthesis Using Motion Distribution Statistics , 2008, J. Res. Pract. Inf. Technol..

[19]  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..

[20]  Mohammad Manzur Murshed,et al.  A motion-based approach for segmenting dynamic textures , 2009 .

[21]  Ashfaqur Rahman,et al.  Multiple temporal texture detection using feature space mapping , 2007, CIVR '07.