3D OBJECT CATEGORIZATION WITH PROBABILISTIC CONTOUR MODELS - Gaussian Mixture Models for 3D Shape Representation

Kerstin Pötsch, Axel Pinz

Abstract

We present a probabilistic framework for learning 3D contour-based category models represented by Gaussian Mixture Models. This idea is motivated by the fact that even small sets of contour fragments can carry enough information for a categorization by a human. Our approach represents an extension of 2D shape based approaches towards 3D to obtain a pose-invariant 3D category model. We reconstruct 3D contour fragments and generate what we call ‘3D contour clouds’ for specific objects. The contours are modeled by probability densities, which are described by Gaussian Mixture Models. Thus, we obtain a probabilistic 3D contour description for each object. We introduce a similarity measure between two probability densities which is based on the probability of intra-class deformations. We show that a probabilistic model allows for flexible modeling of shape by local and global features. Our experimental results show that even with small inter-class difference it is possible to learn one 3D Category Model against another category and thus demonstrate the feasibility of 3D contour-based categorization.

References

  1. Belongie, S., Malik, J., and Puzicha, J. (2002). Shape matching and object recognition using shape contexts. IEEE Trans. PAMI, 24(4):509-522.
  2. Cootes, T. (1999). A mixture model for representing shape variation. Image and Vision Computing, 17(8):567- 573.
  3. DeCarlo, D., Finkelstein, A., Rusinkiewicz, S., and Santella, A. (2003). Suggestive contours for conveying shape. ACM Transactions on Graphics (Proc. SIGGRAPH), 22(3):848-855.
  4. DeCarlo, D. and Rusinkiewicz, S. (2007). Highlight lines for conveying shape. In International Symposium on NPAR.
  5. Ebrahimnezhad, H. and Ghassemian, H. (2007). Robust motion and 3d structure from space curves. ISSPA 2007, pages 1-4.
  6. Fabbri, R. and Kimia, B. B. (2010). 3D curve sketch: Flexible curve-based stereo reconstruction and calibration. In Proceedings of the IEEE CVPR 2010.
  7. Gal, R., Shamir, A., and Cohen-Or, D. (2007a). Poseoblivious shape signature. IEEE TVCG, 13(2):261- 271.
  8. Gal, R., Shamir, A., and Cohen-Or, D. (2007b). Poseoblivious shape signature. IEEE TVCG, 13(2):261- 271.
  9. Goldberger, J., Gordon, S., and Greenspan, H. (2003). An efficient image similarity measure based on approximations of KL-divergence between two gaussian mixtures. In Proc. on ICCV 2003, pages 487 -493 vol.1.
  10. Iyer, N., Jayanti, S., Lou, K., Kalyanaraman, Y., and Ramani, K. (2005). Three-dimensional shape searching: state-of-the-art review and future trends. ComputerAided Design, 37(5):509-530.
  11. Jian, B. and Vemuri, B. (2005). A robust algorithm for point set registration using mixture of Gaussians. In Proc. on ICCV 2005, volume 2, pages 1246 - 1251 Vol. 2.
  12. Kazhdan, M., Funkhouser, T., and Rusinkiewicz, S. (2004). Symmetry descriptors and 3D shape matching. In Symposium on Geometry Processing.
  13. Leibe, B., Leonardis, A., and Schiele, B. (2004). Combined object categorization and segmentation with an implicit shape model. In Workshop on Statistical Learning in Computer Vision, ECCV.
  14. Leordeanu, M., Hebert, M., and Sukthankar, R. (2007). Beyond local appearance: Category recognition from pairwise interactions of simple features. In Proc. of CVPR.
  15. Liebelt, J. and Schmid, C. (2010). Multi-View Object Class Detection with a 3D Geometric Model. In IEEE Conference on CVPR.
  16. Lowe, D. G. and Binford, T. O. (1983). Perceptual Organization as a Basis for Visual Recognition. In AAAI, pages 255-260.
  17. Mahmoudi, M. and Sapiro, G. (2009). Three-dimensional point cloud recognition via distributions of geometric distances. Graph. Models, 71(1):22-31.
  18. Ohbuchi, R., Minamitani, T., and Takei, T. (2005). Shapesimilarity search of 3d models by using enhanced shape functions. In IJCAT, volume 2005, pages 70- 85.
  19. Ohtake, Y., Belyaev, A., and Seidel, H.-P. (2004). Ridgevalley lines on meshes via implicit surface fitting. ACM Trans. Graph., 23(3):609-612.
  20. Opelt, A., Pinz, A., and Zisserman, A. (2006). A boundaryfragment-model for object detection. In Proc. of ECCV.
  21. Osada, R., Funkhouser, T., Chazelle, B., and Dobkin, D. (2002). Shape distributions. ACM Trans. Graph., 21(4):807-832.
  22. Park, J. S. and Han, J. H. (2002). Euclidean reconstruction from contour matches. PR, 35:2109-2124.
  23. Pauly, M., Keiser, R., and Gross, M. H. (2003). Multi-scale feature extraction on point-sampled surfaces. Comput. Graph. Forum, 22(3):281-290.
  24. Ross, S. M. (2005). Introductory Statistics. Academic Press, Inc., Orlando, FL, USA.
  25. Schweighofer, G., Segvic, S., and Pinz, A. (2008). Online/realtime structure and motion for general camera models. IEEE WACV, pages 1-6.
  26. Shilane, P., Min, P., Kazhdan, M., and Funkhouser, T. (2004). The princeton shape benchmark. In Shape Modeling International.
  27. Shotton, J., Blake, A., and Cipolla, R. (2008). MultiScale Categorical Object Recognition Using Contour Fragments. IEEE Transactions on PAMI, 30(7):1270- 1281.
  28. Sundar, H., Silver, D., Gagvani, N., and Dickinson, S. (2003). Skeleton based shape matching and retrieval. SMI 7803: Proceedings of the Shape Modeling International 2003, page 130.
  29. Tangelder, J. and Veltkamp, R. (2007). A survey of content based 3d shape retrieval methods. Multimedia Tools and Applications.
  30. Unger, M., Mauthner, T., Pock, T., and Bischof, H. (2009). Tracking as segmentation of spatial-temporal volumes by anisotropic weighted tv. In 7th International Conference, EMMCVPR, volume 5681 of LNCS, Bonn, Germany. Springer.
  31. Wang, F., Vemuri, B. C., Rangarajan, A., and Eisenschenk, S. J. (2008). Simultaneous Nonrigid Registration of Multiple Point Sets and Atlas Construction. IEEE Trans. PAMI, 30(11):2011-2022.
  32. Xu, L. and Jordan, M. I. (1996). On convergence properties of the em algorithm for gaussian mixtures. Neural Comput., 8(1):129-151.
  33. 5. Stereo Reconstruction. Based on the contour point correspondences we reconstruct the 3D contour fragments using the 'Object Space Error for General Camera Models' (Schweighofer et al., 2008).
  34. 6. S+M Analysis. The robust S+M analysis uses point features and is based on the work by (Schweighofer et al., 2008).
Download


Paper Citation


in Harvard Style

Pötsch K. and Pinz A. (2011). 3D OBJECT CATEGORIZATION WITH PROBABILISTIC CONTOUR MODELS - Gaussian Mixture Models for 3D Shape Representation . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011) ISBN 978-989-8425-47-8, pages 259-270. DOI: 10.5220/0003317402590270


in Bibtex Style

@conference{visapp11,
author={Kerstin Pötsch and Axel Pinz},
title={3D OBJECT CATEGORIZATION WITH PROBABILISTIC CONTOUR MODELS - Gaussian Mixture Models for 3D Shape Representation},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011)},
year={2011},
pages={259-270},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003317402590270},
isbn={978-989-8425-47-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011)
TI - 3D OBJECT CATEGORIZATION WITH PROBABILISTIC CONTOUR MODELS - Gaussian Mixture Models for 3D Shape Representation
SN - 978-989-8425-47-8
AU - Pötsch K.
AU - Pinz A.
PY - 2011
SP - 259
EP - 270
DO - 10.5220/0003317402590270