Advertisement

A Bayesian network for 3d object recognition in range data

  • B. Krebs
  • M. Burkhardt
  • F. M. Wahl
Object Recognition
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1296)

Abstract

Introducing general CAD descriptions in object recognition systems has become a major field of research called CAD based vision (CBV). However, the major problem using free-form object descriptions is how to define recognizable features which can be extracted from sensor data. In this paper we propose new methods for an extraction of 3d space curves from CAD models and from range data. Object identification is performed by correlating feature vectors from significant subcurves. However, features relying on differential surface properties tend to be very vulnerable with respect to noise. To cope with erroneous data we propose to model the statistical behavior of the features using a Bayesian network. Thus, providing a robust and powerful CAD based 3d object recognition system.

Key Words

3d Object Recognition CAD Based Vision (CBV) B-Spline Space Curves Bayesian Networks 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    D. M. Chelberg. Uncertainty in interpretation of range imagery. In Proc. International Conference on Computer Vison, Osaka, Japan, pages 634–657, 1990.Google Scholar
  2. 2.
    C. Dorai and A. K. Jain. Recognition of 3-d free-form objects. In Proc. International Conference on Pattern Recognition, Vienna, Austria, 1996.Google Scholar
  3. 3.
    G. E. Farin. Curves and Surfaces for Computer Aided Geometric Design, a Practical Guide 3rd. ed. Academic Press, New York, 1993.Google Scholar
  4. 4.
    P. J. Flynn and A. K. Jain. 3d object recognition using invariant feature indexing of interpretation tables. Computer Vision, Graphics, and Image Processing, 55(2):119–129, 1992.Google Scholar
  5. 5.
    B. K. P. Horn. Closed-form solution of absolute orientation using unit quaternions. J. Opt. Soc. of America, 4(4):629–642, 1987.Google Scholar
  6. 6.
    F. V. Jensen. An Introduction to Bayesian Networks. UCL Press, 1996.Google Scholar
  7. 7.
    B. Krebs, P. Sieverding, and B. Korn. A fuzzy icp algorithm for 3d free form object recognition. In Proc. International Conference on Pattern Recognition, Vienna, Austria, pages 539–543, 1996.Google Scholar
  8. 8.
    W. B. Mann and T. O. Binford. An example of 3d interpretation of images using bayesian networks. In DARPA Image Understanding Workshop, pages 793–801, 1992.Google Scholar
  9. 9.
    J. Mao, A. K. Jain, and P. J. Flynn. Integration of multiple feature groups and multiple views into an 3d object recognition system. In Proc.CAD-Based Vision Workshop, Champion, Pennsylvania, pages 184–192, 1994.Google Scholar
  10. 10.
    K. G. Olesen, S. L. Lauritzen, and F. V. Jensen. Hugin: A system creating adaptive causual probabilistic networks. In Proc. International Conference on Uncertainty in Artificial Intelligence, pages 223–229, 1992.Google Scholar
  11. 11.
    S. Sakar and K. L. Boyer. Computing Perceptual Organization in Computer Vision. World Scientific, 1994.Google Scholar
  12. 12.
    L. G. Shapiro, S. L. Tanimoto, and J. F. Brinkley. A visual database system for data experiment management in model-based computer vision. In Proc.CADBased Vision Workshop, Champion, Pennsylvania, pages 64–74, 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • B. Krebs
    • 1
  • M. Burkhardt
    • 1
  • F. M. Wahl
    • 1
  1. 1.Institute for Robotics and Computer ControlTechnical University BraunschweigBraunschweigGermany

Personalised recommendations