Advertisement

3D Object Class Geometry Modeling with Spatial Latent Dirichlet Markov Random Fields

  • Hanchen Xiong
  • Sandor Szedmak
  • Justus Piater
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8142)

Abstract

This paper presents a novel part-based geometry model for 3D object classes based on latent Dirichlet allocation (LDA). With all object instances of the same category aligned to a canonical pose, the bounding box is discretized to form a 3D space dictionary for LDA. To enhance the spatial coherence of each part during model learning, we extend LDA by strategically constructing a Markov random field (MRF) on the part labels, and adding an extra spatial parameter for each part. We refer to the improved model as spatial latent Dirichlet Markov random fields (SLDMRF). The experimental results demonstrate that SLDMRF exhibits superior semantic interpretation and discriminative ability in model classification to LDA and other related models.

Keywords

Point Cloud Markov Random Field Latent Dirichlet Allocation Spatial Coherence 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.
    Blei, D., Ng, A., Jordan, M.: Latent Dirichlet Allocation. Journal of Machine Learning Research 3, 993–1022 (2003)zbMATHGoogle Scholar
  2. 2.
    Detry, R., Piater, J.: Continuous surface-point distributions for 3D object pose estimation and recognition. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part III. LNCS, vol. 6494, pp. 572–585. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  3. 3.
    Detry, R., Pugeault, N., Piater, J.: A Probabilistic Framework for 3D Visual Object Representation. PAMI 31(10), 1790–1803 (2009)CrossRefGoogle Scholar
  4. 4.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object Detection with Discriminatively Trained Part-Based Models. PAMI 32(9), 1627–1645 (2010)CrossRefGoogle Scholar
  5. 5.
    Golovinskiy, A., Funkhouser, T.A.: Consistent segmentation of 3D models. Computers and Graphics 33, 262–269 (2009)CrossRefGoogle Scholar
  6. 6.
    Griffiths, T.L., Steyvers, M.: Finding scientific topics. Proceedings of the National Academy of Sciences 101(suppl. 1), 5228–5235 (2004)CrossRefGoogle Scholar
  7. 7.
    Liebelt, J., Schmid, C.: Multi-View Object Class Detection with a 3D Geometric Model. In: CVPR (2010)Google Scholar
  8. 8.
    Mackey, L.: Latent Dirichlet Markov Random Fields for Semi-supervised Image Segmentation and Object Recognition (2007)Google Scholar
  9. 9.
    Shilane, P., Min, P., Kazhdan, M.M., Funkhouser, T.A.: The Princeton Shape Benchmark. In: SMI, pp. 167–178. IEEE Computer Society (2004)Google Scholar
  10. 10.
    Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering object categories in image collections. In: ICCV (2005)Google Scholar
  11. 11.
    Wang, X., Grimson, E.: Spatial Latent Dirichlet Allocation. In: NIPS (2007)Google Scholar
  12. 12.
    Xiong, H., Szedmak, S., Piater, J.: Efficient,General Point Cloud Registration with Kernel Feature Maps. In: Canadian Conf. on Computer and Robot Vision (2013)Google Scholar
  13. 13.
    Yan, P., Khan, S.M., Shah, M.: 3D model based object class detection in an arbitrary view. In: ICCV (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Hanchen Xiong
    • 1
  • Sandor Szedmak
    • 1
  • Justus Piater
    • 1
  1. 1.Institute of Computer ScienceUniversity of InnsbruckAustria

Personalised recommendations