A novel approach to junction detection using an explicit line finder model and contextual rules is presented. Contextual rules expressing properties of 3D-edges (surface orientation discontinuities) limit the num- ber of line intersections interpreted as junctions. Probabilistic relaxation labelling scheme is used to combine the a priori world knowledge represented by contextual rules and the information contained in observed lines.
Junctions corresponding to a vertex (V-junctions) and an occlusion (T-junctions) of a 3D object are detected and stored in a junction graph. The information in the junction graph is used to extract higher level features. Results of the most promising method, the polyhedral object face recovery, are briefly discussed. The performance of the junction detection process is demonstrated on images from indoor, outdoor, and industrial environments.
KeywordsLine Intersection Editing
Unable to display preview. Download preview PDF.
- C. Coelho, M. Straforini, and M. Campani. Using geometrical rules and a priori knowledge for the understanding of indoor scenes. In Proc. British Machine Vision Conference ,pages 229–234, 1990.Google Scholar
- R.N. Haber and M. Hershenson. The Psychology of Visual Perception. Holt, Rinehart and Winston Inc., U.S.A, 1973.Google Scholar
- R. Horaud, F. Veillon, and T. Skordas. Finding geometric and relational structures in an image. In European Conference on Computer Vision ,pages 373–384, 1990.Google Scholar
- J. Kittler, J. Illingworth, J. Matas, P. Remagnino, K. C. Wong, H. Christensen, J-O. Eklundh, G. Olofsonn, and M. Li. Symbolic scene interpretation and control of perception. Technical report, ESPRIT BRA Project 3038, March 1992.Google Scholar
- Du Li, G.D. Sullivan, and K.D. Baker. Edge detection at junctions. In AVC ,pages 121–125, 1989.Google Scholar
- J. A. Nobel. Finding corners. In AVC ,pages 267–274, 1988.Google Scholar
- P. L. Palmer, J. Kittler, and M. Petrou. A Hough transform algorithm with a 2D hypothesis testing kernel. In Proceedings of IEEE International Conference Pattern Recognition ,September 1992.Google Scholar
- J.R Pomerantz. Perceptual organization and information processing. In Perceptual Organization ,pages 141–180, 365 Broadway, Hillsdale, New Jersey, 1981. Lawrence ERLBRAUM associates.Google Scholar
- J. Princen. Hough Transform Methods for Curve Detection and Parameter Estimation. PhD thesis, University of Surrey, June 1990.Google Scholar
- VAP project. Vision as process. Technical annex, EEC, March 1989.Google Scholar