Integration of Multiple Feature Detection by a Bayesian Net for 3d Object Recognition
This paper proposes a general framework to build a 3d object recognition system from a set of CAD object definitions. Various, reliable features from object corners, edges and 3d rim curves are introduced which provide sufficient information to allow identification and pose estimation of CAD designed industrial parts. As features relying on differential surface properties tend to be very vulnerable with respect to noise, we model the statistical behavior of the data by means of Bayesian nets, representing the relations between objects and observable features. This allows to identify objects by a combination of several features considering the significance of each single feature with respect to the object model base. On this basis robust and powerful 3d CAD based object recognition systems can be build.
Unable to display preview. Download preview PDF.
- 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
- 3.G. E. Farm. Curves and Surfaces for Computer Aided Geometric Design, a Practical Guide 3rd. ed. Academic Press, New York, 1993.Google Scholar
- 6.B. Krebs, M. Burkhardt, and F. M. Wahl. A bayesian network for 3d object recognition in range data. In Proc. International Conference on Computer Analysis of Images and Patterns, Kiel, Germany, pages 361–368, 1997.Google Scholar
- 7.B. Krebs, B. Korn, and M. Burkhardt. A task driven 3d object recognition system using bayesian networks. In Proc. International Conference on Computer Vison, Bombay, India, pages 527–532, 1998.Google Scholar
- 8.B. Krebs, B. Korn, and F.M. Wahl. 3d b-spline curve matching for model based object recognition. In Proc. International Conference on Image Processing, Santa Barbara, USA, pages 716–719, 1997.Google Scholar
- 10.B. Krebs and F. M. Wahl. Advances in Computer Vision, chapter CAD Based 3d Object Recognition on Range Images, pages 221–230. Advances in Computer Science. Springer, 1997.Google Scholar
- 11.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
- 13.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