Dynamic Textures Segmentation with GPU

  • Juan Manuel Rodríguez
  • Francisco Gómez Fernández
  • María Elena Buemi
  • Julio Jacobo-Berlles
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7441)


This work addresses the problem of motion segmentation in video sequences using dynamic textures. Motion can be globally modeled as a statistical visual process know as dynamic texture. Specifically, we use the mixtures of dynamic textures model which can simultaneously handle different visual processes. Nowadays, GPU are becoming increasingly popular in computer vision applications because of their cost-benefit ratio. However, GPU programming is not a trivial task and not all algorithms can be easily switched to GPU. In this paper, we made two implementations of a known motion segmentation algorithm based on mixtures of dynamic textures. One using CPU and the other ported to GPU. The performance analyses show the scenarios for which it is worthwhile to do the full GPU implementation of the motion segmentation process.


Video Sequence Visual Process Hide State Cholesky Factorization Rand Index 
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.


  1. 1.
    Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artificial Intelligence 17(1-3), 185–203 (1981)CrossRefGoogle Scholar
  2. 2.
    Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: IJCAI 1981, pp. 674–679 (1981)Google Scholar
  3. 3.
    Doretto, G.: Dynamic textures: Modeling, learning, synthesis, animation, segmentation, and recognition, Thesis (Ph.D.)–University of California, Los AngelesGoogle Scholar
  4. 4.
    Chan, A.B., Vasconcelos, N.: Modeling, clustering, and segmenting video with mixtures of dynamic textures. PAMI 30 (May 2008)Google Scholar
  5. 5.
    Chan, A.B., Vasconcelos, N.: Variational layered dynamic textures. In: CVPR, pp. 1062–1069 (June 2009)Google Scholar
  6. 6.
    Roweis, S., Ghahramani, Z.: A unifying review of linear Gaussian models. Neural Comput. 11(2), 305–345 (1999)CrossRefGoogle Scholar
  7. 7.
    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum Likelihood from Incomplete Data via the EM Algorithm. J. Roy. Statist. Soc. Ser. B, Meth. 39(1), 1–38 (1977)MathSciNetzbMATHGoogle Scholar
  8. 8.
    Chan, A.: Synthetic Dynamic Texture Segmentation Database (July 2009),
  9. 9.
    Hubert, L., Arabie, P.: Comparing partitions (1985)Google Scholar
  10. 10.
    Huang, M.-Y., Wei, S.-C., Huang, B., Chang, Y.-L.: Accelerating the Kalman Filter on a GPU. In: ICPADS (2011)Google Scholar
  11. 11.
    Bouckaert, R.: Matrix inverse with Cuda and CUBLAS,
  12. 12.
    Ltaief, H., Tomov, S., Nath, R., Du, P., Dongarra, J.: A Scalable High Performant Cholesky Factorization for Multicore with GPU Accelerators. In: Palma, J.M.L.M., Daydé, M., Marques, O., Lopes, J.C. (eds.) VECPAR 2010. LNCS, vol. 6449, pp. 93–101. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  13. 13.
    NVIDIA, Cuda cublas library, Version 4.1 (January 2012)Google Scholar
  14. 14.
    Chan, A.B., Vasconcelos, N.: Layered Dynamic Textures. IEEE Transactions on Pattern Analysis and Machine Intelligence 31, 1862–1879 (2009)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Juan Manuel Rodríguez
    • 1
  • Francisco Gómez Fernández
    • 1
  • María Elena Buemi
    • 1
  • Julio Jacobo-Berlles
    • 1
  1. 1.Departamento de Computación, Facultad de Ciencias Exactas y NaturalesUniversidad de Buenos AiresBuenos AiresArgentina

Personalised recommendations