Extraction of parametric descriptions of circular GCS from a pair of contours for 3-D shape recognition

This paper addresses the issue of recognizing 3-D (three-dimensional) shapes of objects from their 2-D contour pairs. A shape model, that is represented by a family of spheres of varying radii with their centers on its axis, is developed for the shape class of circular Generalized Cones (GCs) with a space-curved axis. The quasi-invariant property of the shape model is defined and is used to recover the 3-D shapes of the object class by solving the problem of stereo-matching between their contour pairs. The recovered shapes are represented by a set of their parametric primitives and spatial relations between them, so that they may be used for recognition even under occluded environment.

[1]  F. Bookstein.  The line-skeleton , 1979 .

[2]  D. T. Lee,et al.  Medial Axis Transformation of a Planar Shape , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  S. Fukushima,et al.  Estimating the three-dimensional shape from a silhouette by geometrical division of the plane , 1991, Proceedings IECON '91: 1991 International Conference on Industrial Electronics, Control and Instrumentation.

[4]  R. Nevatia,et al.  Quasi-invariant properties and 3-D shape recovery of non-straight, non-constant generalized cylinders , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Jean Ponce,et al.  Invariant Properties of Straight Homogeneous Generalized Cylinders and Their Contours , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  John Fairfield,et al.  Segmenting Dot Patterns by Voronoi Diagram Concavity , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  M. Brady,et al.  Smoothed Local Symmetries and Their Implementation , 1984 .

[8]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[9]  Yoshinobu Sato,et al.  Smoothed local generalized cones: an axial representation of 3D shapes , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  John Fairfield.  Segmenting blobs into subregions , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[11]  S. Shafer.  Shadows and Silhouettes in Computer Vision , 1985 .

[12]  Jean Ponce,et al.  Finding the limbs and cusps of generalized cylinders , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[13]  Ramakant Nevatia,et al.  Recovering shape from contour for constant cross section generalized cylinders , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Takeo Kanade,et al.  Stereo by Intra- and Inter-Scanline Search Using Dynamic Programming , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Vishvjit S. Nalwa.  Line-Drawing Interpretation: Bilateral Symmetry , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Gérard G. Medioni,et al.  Useful geometric properties of the generalized cone , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[18]  Gabor T. Herman,et al.  Image Reconstruction From Projections , 1975, Real Time Imaging.

[19]  Nasser Kehtarnavaz,et al.  A 3-D Contour Segmentation Scheme Based on Curvature and Torsion , 1988, IEEE Trans. Pattern Anal. Mach. Intell..