Advertisement

Exploiting Repetitive Object Patterns for Model Compression and Completion

  • Luciano Spinello
  • Rudolph Triebel
  • Dizan Vasquez
  • Kai O. Arras
  • Roland Siegwart
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6315)

Abstract

Many man-made and natural structures consist of similar elements arranged in regular patterns. In this paper we present an unsupervised approach for discovering and reasoning on repetitive patterns of objects in a single image. We propose an unsupervised detection technique based on a voting scheme of image descriptors. We then introduce the concept of latticelets: minimal sets of arcs that generalize the connectivity of repetitive patterns. Latticelets are used for building polygonal cycles where the smallest cycles define the sought groups of repetitive elements. The proposed method can be used for pattern prediction and completion and high-level image compression. Conditional Random Fields are used as a formalism to predict the location of elements at places where they are partially occluded or detected with very low confidence. Model compression is achieved by extracting and efficiently representing the repetitive structures in the image. Our method has been tested on simulated and real data and the quantitative and qualitative result show the effectiveness of the approach.

Keywords

Repetitive Element Conditional Random Field Closed Contour Repetitive Pattern Object Instance 
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.

References

  1. 1.
    Leibe, B., Leonardis, A., Schiele, B.: Combined object categorization and segmentation with an implicit shape model. In: ECCV Workshop on Stat. Learn. in Comp. Vis. (2004)Google Scholar
  2. 2.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmentation and labeling sequence data. In: Int. Conf. on Mach. Learn. (ICML) (2001)Google Scholar
  3. 3.
    Dick, A.R., Torr, P.H.S., Cipolla, R.: Modelling and interpretation of architecture from several images. Int. Journ. of Comp. Vis. 60, 111–134 (2004)CrossRefGoogle Scholar
  4. 4.
    Mayer, H., Reznik, S.: Building facade interpretation from image sequences. In: ISPRS Workshop CMRT 2005 (2005)Google Scholar
  5. 5.
    Xiao, J., Fang, T., Tan, P., Zhao, P., Ofek, E., Quan, L.: Image-based façade modeling. In: ACM SIGGRAPH Asia (2008)Google Scholar
  6. 6.
    Wonka, P., Wimmer, M., Sillion, F., Ribarsky, W.: Instant architecture. ACM Trans. Graph. 22, 669–677 (2003)CrossRefGoogle Scholar
  7. 7.
    Müller, P., Zeng, G., Wonka, P., Van Gool, L.: Image-based procedural modeling of facades. ACM Trans. Graph. 26, 85 (2007)CrossRefGoogle Scholar
  8. 8.
    Schaffalitzky, F., Zisserman, A.: Geometric grouping of repeated elements within images. In: British Machine Vision Conf. (1999)Google Scholar
  9. 9.
    Turina, A., Tuytelaars, T., Van Gool, L.: Efficient grouping under perspective skew. In: IEEE Conf. on Comp. Vis. and Pat. Recog. (CVPR) (2001)Google Scholar
  10. 10.
    Liu, Y., Collins, R.T., Tsin, Y.: A computational model for periodic pattern perception based on frieze and wallpaper groups. IEEE Trans. Pattern An. & Mach. Intell. 26, 354–371 (2004)CrossRefGoogle Scholar
  11. 11.
    Hays, J., Leordeanu, M., Efros, A.A., Liu, Y.: Discovering texture regularity as a higher-order correspondence problem. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 522–535. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  12. 12.
    Korah, T., Rasmussen, C.: Analysis of building textures for reconstructing partially occluded facades. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 359–372. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  13. 13.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. Pattern An. & Mach. Intell. 24, 509–522 (2002)CrossRefGoogle Scholar
  14. 14.
    Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8, 679–698 (1986)CrossRefGoogle Scholar
  15. 15.
    Freeman, H.: On the encoding of arbitrary geometric configurations. IEEE Trans. Electr. Computers EC-10, 260–268 (1961)CrossRefMathSciNetGoogle Scholar
  16. 16.
    Spinello, L., Triebel, R., Siegwart, R.: Multimodal people detection and tracking in crowded scenes. In: Proc. of the AAAI Conf. on Artificial Intelligence (2008)Google Scholar
  17. 17.
    Kruskal, J.B.: On the shortest spanning subtree of a graph and the traveling salesman problem. Proceedings of the American Mathematical Society 7, 48–50 (1956)MathSciNetGoogle Scholar
  18. 18.
    Collins, R., Beveridge, J.: Matching persp. views of copl. structures using projective unwarping and sim. matching. In: IEEE Conf. on Comp. Vis. and Pat. Recog. (CVPR) (1993)Google Scholar
  19. 19.
    Fletcher, R.: Practical Methods of Optimization. Wiley, Chichester (1987)zbMATHGoogle Scholar
  20. 20.
    Pearl, J.: Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann Publishers Inc., San Francisco (1988)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Luciano Spinello
    • 1
    • 2
  • Rudolph Triebel
    • 2
  • Dizan Vasquez
    • 3
  • Kai O. Arras
    • 1
  • Roland Siegwart
    • 2
  1. 1.Social Robotics LabUniversity of FreiburgGermany
  2. 2.Autonomous Systems LabETH ZurichSwitzerland
  3. 3.ITESM Campus CuernavacaMexico

Personalised recommendations