Advertisement

Adaptive Point-Cloud Surface Interpretation

  • Q. Meng
  • B. Li
  • H. Holstein
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4035)

Abstract

We present a novel adaptive radial basis function network to reconstruct smooth closed surfaces and complete meshes from non-uniformly sampled noisy range data. The network is established using a heuristic learning strategy. Neurons can be inserted, removed or updated iteratively, adapting to the complexity and distribution of the underlying data. This flexibility is particularly suited to highly variable spatial frequencies, and is conducive to data compression with network representations. In addition, a greedy neighbourhood Extended Kalman Filter learning method is investigated, leading to a significant reduction of computational cost in the training process with desired prediction accuracy. Experimental results demonstrate the performance advantages of compact network representation for surface reconstruction from large amount of non-uniformly sampled incomplete point-clouds.

Keywords

Radial Basis Function Surface Reconstruction Radial Basis Function Neural Network Radial Basis Function Network Hide Unit 
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.
    Musavi, M., Ahmed, W., Chan, K., Faris, K., Hummels, D.: On the training of radial basis function classifiers. Neural Networks 5(4), 595–603 (1992)CrossRefGoogle Scholar
  2. 2.
    Chen, S., Billings, S., Grant, P.: Recursive hybrid algorithm for non-linear system identification using radial basis function networks. Int. J. Control 55, 1051–1070 (1992)MATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Blinn, J.: A generalization of algebraic surface drawing. ACM Trans. Graph. 1(3), 235–256 (1982)CrossRefGoogle Scholar
  4. 4.
    Muraki, S.: Volumetric shape description of range data using blobby model. In: Proc. ACM SIGGRAPH (1991)Google Scholar
  5. 5.
    Lim, C., Turkiyyah, G., Ganter, M., Storti, D.: Implicit reconstruction of solids from cloud point sets. In: Proc. of the third ACM symposium on Solid modeling and applications, pp. 393–402 (1995)Google Scholar
  6. 6.
    Sharf, A., Alexa, M., Cohen-Or, D.: Context-based surface completion. ACM Trans. Graph. 23(3), 878–887 (2004)CrossRefGoogle Scholar
  7. 7.
    Kojekine, N., Hagiwara, I., Savchenko, V.: Software tools using csrbf for processing scattered data. Computer & Graphics 27(2), 463–470 (2003)CrossRefGoogle Scholar
  8. 8.
    Turk, G., O’Brien, J.: Modelling with implicit surfaces that interpolate. ACM Trans. on Graphics 21(4), 855–873 (2002)CrossRefGoogle Scholar
  9. 9.
    Ohtake, Y., Belyaev, A., Seidel, H.: A multi-scale approach to 3D scattered data interpolation with compactly supported basis functions. In: SMI 2003: Proc. Shape Modeling International, Washington, DC, USA, pp. 153–164. IEEE Computer Society Press, Los Alamitos (2003)CrossRefGoogle Scholar
  10. 10.
    Ohtake, Y., Belyaev, A., Alexa, M., Turk, G., Seidel, H.: Multi-level partition of unity implicits. ACM Trans. Graph. 22(3), 463–470 (2003)CrossRefGoogle Scholar
  11. 11.
    Carr, J., Beatson, R., Cherrie, J., Mitchell, T., Fright, W., McCallum, B., Evans, T.: Reconstruction and representation of 3D objects with radial basis functions. In: ACM SIGGRAPH, pp. 67–76 (2001)Google Scholar
  12. 12.
    Ferrari, S., Maggioni, M., Borghese, N.A.: Multiscale approximation with hierarchical radial basis functions networks. IEEE Trans. on Neural Networks 15(1), 178–188 (2004)CrossRefGoogle Scholar
  13. 13.
    Bors, A., Gabbouj, M.: Minimal topology for a radial basis functions neural network for pattern classification. Digital Signal Processing 4(3), 173–188 (1994)CrossRefGoogle Scholar
  14. 14.
    Platt, J.: A resource-allocating network for function interpolation. Neural Comput. 3(2), 213–225 (1991)CrossRefMathSciNetGoogle Scholar
  15. 15.
    Kadirkamanathan, V., Niranjan, M.: A function estimation approach to sequential learning with neural networks. Neural Computation 5(6), 954–975 (1993)CrossRefGoogle Scholar
  16. 16.
    Lu, Y., Sundararajan, N., Saratchandran, P.: A sequential learning scheme for function approximation using minimal radial basis function neural networks. Neural Comput. 9(2), 461–478 (1997)MATHCrossRefGoogle Scholar
  17. 17.
    Karayiannis, N.: Reformulated radial basis neural networks trained by gradient descent. IEEE Trans. on Neural Networks 10(3), 657–671 (1999)CrossRefGoogle Scholar
  18. 18.
    Simon, D.: Training radial basis neural networks with the extended Kalman filter. Neurocomputing 48, 455–475 (2002)MATHCrossRefGoogle Scholar
  19. 19.
    Lu, Y., Sundararajan, N., Saratchandran, P.: Performance evaluation of a sequential minimal radial basis function (rbf) neural network learning algorithm. IEEE Trans. Neural Networks 9(2), 308–318 (1998)CrossRefGoogle Scholar
  20. 20.
    Haykin, S.: Kalman filtering and neural networks. Wiley Intercience, Chichester (2001)CrossRefGoogle Scholar
  21. 21.
    Range image database at Ohio SAMPL, http://sampl.ece.ohio-state.edu/data/3DDB/RID/minolta

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Q. Meng
    • 1
  • B. Li
    • 2
  • H. Holstein
    • 1
  1. 1.Dept. of Computer ScienceUniversity of WalesAberystwythU.K
  2. 2.Dept. of Computing and MathematicsManchester Metropolitan UniversityU.K

Personalised recommendations