A Comparison on Textured Motion Classification

  • Kaan Öztekin
  • Gözde Bozdağı Akar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4105)


Textured motion – generally known as dynamic or temporal texture – analysis, classification, synthesis, segmentation and recognition is popular research areas in several fields such as computer vision, robotics, animation, multimedia databases etc. In the literature, several algorithms are proposed to characterize these textured motions such as stochastic and deterministic algorithms. However, there is no study which compares the performances of these algorithms. In this paper, we carry out a complete comparison study. Also, improvements to deterministic methods are given.


Recognition Rate Optical Flow Dynamic Texture Regular Texture Gray Level Difference 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Doretto, G.: Dynamic Texture Modeling., M.S. Thesis, University of California (2002)Google Scholar
  2. 2.
    Cock, K.D., Moor, B.D.: Subspace angles between linear stochastic models. In: Proceedings of 39th IEEE Conference on Decision and Control, pp. 1561–1566 (2000)Google Scholar
  3. 3.
    Martin, R.J.: A Metric for ARMA Processes. IEEE Transactions On Signal Processing 48(4), 1164–1170 (2000)MATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Peteri, R., Chetverikov, D.: Dynamic texture recognition using normal flow and texture regularity. In: Marques, J.S., Pérez de la Blanca, N., Pina, P. (eds.) IbPRIA 2005. LNCS, vol. 3523, pp. 223–230. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  5. 5.
    Chetverikov, D.: Pattern Regularity as a Visual Key. Image and Vision Computing 18, 975–985 (2000)CrossRefGoogle Scholar
  6. 6.
    Horn, B.K.P., Schunck, B.G.: Determining Optical Flow. Artificial Intelligence 17, 185–203 (1981)CrossRefGoogle Scholar
  7. 7.
    Sookocheff, K.B.: Computing Texture Regularity. Image Processing and Computer Vision (2004)Google Scholar
  8. 8.
    Fazekas, S., Chetverikov, D.: Normal Versus Complete Flow In Dynamic Texture Recognition: A Comparative Study. In: 4th International Workshop on Texture Analysis and Synthesis (2005)Google Scholar
  9. 9.
    Chetverikov, D., Hanbury, A.: Finding Defects in Texture Using Regularity and Local Orientation. Pattern Recognition 35, 203–218 (2002)CrossRefGoogle Scholar
  10. 10.
    Otsuka, K., Horikoshi, T., Suzuki, S., Fujii, M.: Feature Extraction of Temporal Texture Based On Spatiotemporal Motion Trajectory. In: Int. Conf. on Pattern Recog. ICPR 1998, vol. 2, pp. 1047–1051 (1998)Google Scholar
  11. 11.
    MIT Temporal Texture Database (last visited on November 2005),
  12. 12.
    Brodatz Texture Database (last visited on November 2005),
  13. 13.
    Nelson, R.C., Polana, R.: Qualitative Recognition of Motion using Temporal Texture. CVGIP: Image Understanding 56, 78–89 (1992)MATHCrossRefGoogle Scholar
  14. 14.
    Wildes, R.P., Bergen, J.R.: Qualitative Spatiotemporal Analysis using an Oriented Energy Representation. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 768–784. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  15. 15.
    Smith, J.R., Lin, C.-Y., Naphade, M.: Video Texture Indexing using Spatiotemporal Wavelets. In: IEEE Int. Conf. on Image Processing, ICIP 2002, vol. 2, pp. 437–440 (2002)Google Scholar
  16. 16., (last visited on November 2005)

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Kaan Öztekin
    • 1
  • Gözde Bozdağı Akar
    • 1
  1. 1.Department of Electrical and Electronics EngineeringMiddle East Technical University 

Personalised recommendations