Advertisement

Maximum Margin Distance Learning for Dynamic Texture Recognition

  • Bernard Ghanem
  • Narendra Ahuja
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6312)

Abstract

The range space of dynamic textures spans spatiotemporal phenomena that vary along three fundamental dimensions: spatial texture, spatial texture layout, and dynamics. By describing each dimension with appropriate spatial or temporal features and by equipping it with a suitable distance measure, elementary distances (one for each dimension) between dynamic texture sequences can be computed. In this paper, we address the problem of dynamic texture (DT) recognition by learning linear combinations of these elementary distances. By learning weights to these distances, we shed light on how “salient” (in a discriminative manner) each DT dimension is in representing classes of dynamic textures. To do this, we propose an efficient maximum margin distance learning (MMDL) method based on the Pegasos algorithm [1], for both class-independent and class-dependent weight learning. In contrast to popular MMDL methods, which enforce restrictive distance constraints and have a computational complexity that is cubic in the number of training samples, we show that our method, called DL-PEGASOS, can handle more general distance constraints with a computational complexity that can be made linear. When class dependent weights are learned, we show that, for certain classes of DTs , spatial texture features are dominantly “salient”, while for other classes, this “saliency” lies in their temporal features. Furthermore, DL-PEGASOS outperforms state-of-the-art recognition methods on the UCLA benchmark DT dataset. By learning class independent weights, we show that this benchmark does not offer much variety along the three DT dimensions, thus, motivating the proposal of a new DT dataset, called DynTex++.

Keywords

Recognition Rate Local Binary Pattern Distance Constraint Linear Dynamical System Texture Element 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

978-3-642-15552-9_17_MOESM1_ESM.rtf (6 kb)
Electronic Supplementary Material (7 KB)
978-3-642-15552-9_17_MOESM2_ESM.rtf (2 kb)
Electronic Supplementary Material (2 KB)

References

  1. 1.
    Shalev-Shwartz, S., Singer, Y., Srebro, N.: Pegasos: Primal estimated sub-gradient solver for svm. In: ICML (2007)Google Scholar
  2. 2.
    Ghanem, B., Ahuja, N.: Extracting a fluid dynamic texture and the background from video. In: CVPR (2008)Google Scholar
  3. 3.
    Soatto, S., Doretto, G., Wu, Y.N.: Dynamic textures. IJCV 51, 91–109 (2003)zbMATHCrossRefGoogle Scholar
  4. 4.
    Chetverikov, D., Peteri, R.: A brief survey of dynamic texture description and recognition. In: International Conference on Computer Recognition Systems (2005)Google Scholar
  5. 5.
    Saisan, P., Doretto, G., Wu, Y.N., Soatto, S.: Dynamic texture recognition. In: CVPR, pp. 58–63 (2001)Google Scholar
  6. 6.
    Martin, R.J.: A metric for arma processes. IEEE Trans. on Signal Processing 48, 1164–1170 (2000)zbMATHCrossRefGoogle Scholar
  7. 7.
    Chan, A.B., Vasconcelos, N.: Probabilistic kernels for the classification of auto-regressive visual processes. CVPR 1, 846–851 (2005)Google Scholar
  8. 8.
    Woolfe, F., Fitzgibbon, A.W.: Shift-invariant dynamic texture recognition. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 549–562. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  9. 9.
    Ravichandran, A., Chaudhry, R., Vidal, R.: View-invariant dynamic texture recognition using a bag of dynamical systems. In: CVPR, pp. 1651–1657 (2009)Google Scholar
  10. 10.
    Peteri, R., Chetverikov, D.: Dynamic texture recognition using normal flow and texture regularity. In: Iberian Conference on Pattern Recognition and Image Analysis (2005)Google Scholar
  11. 11.
    Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray scale and rotation invariant texture analysis with local binary patterns. TPAMI 24, 971–987 (2002)Google Scholar
  12. 12.
    Zhao, G., Pietikainen, M.: Local binary pattern descriptors for dynamic texture recognition. In: ICPR, vol. 2, pp. 211–214 (2006)Google Scholar
  13. 13.
    Zhao, G., Pietikainen, M.: Dynamic texture recognition using local binary patterns with an application to facial expressions. TPAMI 29, 915–928 (2007)Google Scholar
  14. 14.
    Frome, A., Singer, Y., Sha, F., Malik, J.: Image retrieval and classification using local distance functions. In: NIPS (2006)Google Scholar
  15. 15.
    Frome, A., Singer, Y., Sha, F., Malik, J.: Learning globally-consistent local distance functions for shape-based image retrieval and classification. In: ICCV (2007)Google Scholar
  16. 16.
    Gu, C., Lim, J.J., Arbelaez, P., Malik, J.: Recognition using regions. In: CVPR, pp. 1030–1037. IEEE, Los Alamitos (2009)Google Scholar
  17. 17.
    Varma, M., Ray, D.: Learning the discriminative power-invariance trade-off. In: ICCV (2007)Google Scholar
  18. 18.
    Vedaldi, A., Gulshan, V., Varma, M., Zisserman, A.: Multiple kernels for object detection. In: ICCV (2009)Google Scholar
  19. 19.
    Rubner, Y., Tomasi, C., Guibas, L.J.: A metric for distributions with applications to image databases. In: ICCV (1998)Google Scholar
  20. 20.
    Zhao, G., Pietikainen, M.: Dynamic texture recognition using volume local binary patterns. In: ECCV, Workshop on Dynamical Vision, pp. 12–23 (2006)Google Scholar
  21. 21.
    Wang, X., Han, T.X., Yan, S.: An hog-lbp human detector with partial occlusion handling. In: ICCV (2009)Google Scholar
  22. 22.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)Google Scholar
  23. 23.
    Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. In: CIVR (2007)Google Scholar
  24. 24.
    Chan, A.B., Vasconcelos, N.: Classifying video with kernel dynamic textures. In: CVPR, vol. 1 (2007)Google Scholar
  25. 25.
    Peteri, R., Huiskes, M., Fazekas, S.: DynTex: the Centre for Mathematics and Computer Science (CWI), Amsterdam (2006), http://www.cwi.nl/projects/dyntex/
  26. 26.
    Gautama, T., Hulle, M.A.V.: A phase-based approach to the estimation of the optical flow field using spatial filtering. TNN 13, 1127–1136 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Bernard Ghanem
    • 1
  • Narendra Ahuja
    • 1
  1. 1.Department of Electrical and Computer EngineeringUniversity of Illinois at Urbana-ChampaignUrbanaUSA

Personalised recommendations