Contextual Junction Finder

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 number 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.

[1]  Ramakant Nevatia,et al.  Using Perceptual Organization to Extract 3-D Structures , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  P. Gács,et al.  Algorithms , 1992 .

[3]  Radu Horaud,et al.  Finding Geometric and Relational Structures in an Image , 1990, ECCV.

[4]  Rachid Deriche,et al.  Using Canny's criteria to derive a recursively implemented optimal edge detector , 1987, International Journal of Computer Vision.

[5]  Josef Kittler,et al.  Combining Evidence in Probabilistic Relaxation , 1989, Int. J. Pattern Recognit. Artif. Intell..

[6]  Li Du,et al.  Edge Detection at Junctions , 1989, Alvey Vision Conference.

[7]  J. Alison Noble,et al.  Finding Corners , 1988, Alvey Vision Conference.

[8]  John Princen.  Hough Transform Methods for Curve Detection and Parameter Estimation , 1990 .

[9]  R. Haber,et al.  The psychology of visual perception , 1973 .

[10]  Josef Kittler,et al.  A Hough transform algorithm with a 2D hypothesis testing kernel , 1993 .

[11]  Robert Bergevin,et al.  Extraction of line drawing features for object recognition , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[12]  David G. Lowe,et al.  Three-Dimensional Object Recognition from Single Two-Dimensional Images , 1987, Artif. Intell..

[13]  C. Coelho,et al.  Using geometrical rules and a priori knowledge for the understanding of indoor scenes , 1990, BMVC.