Obtaining generic parts from range data using a multiview representation

A method is proposed for obtaining a generic-part based 3-D object representation from range images. A small number of 3-D shape types based on geons are the basic part primitives. Surface segmentation of the range image is performed based on the method of Hoffman and Jain. The surfaces are classified into five types based on their principal curvatures, and adjacent surfaces belonging to different parts are separated by examining the surface types and the angle between them, and referring to the characteristic views stored in a small catalog of views of the part primitives. Finally, each part is identified by drawing inferences from surface types, as well as from the distribution of the angles between the part's principal axis and the normals on the side surfaces of that part.

[1]  D. Marr,et al.  Representation and recognition of the spatial organization of three-dimensional shapes , 1978, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[2]  Charles R. Dyer,et al.  3-D multiview object representations for model-based object recognition , 1987, Pattern Recognit..

[3]  Louise Stark,et al.  Developing the aspect graph representation for use in image understanding , 1989 .

[4]  Alex Pentland,et al.  Perceptual Organization and the Representation of Natural Form , 1986, Artif. Intell..

[5]  Rodney A. Brooks,et al.  Model-Based Three-Dimensional Interpretations of Two-Dimensional Images , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Ting-Jun Fan.  Surface Segmentation and Description , 1990 .

[7]  Wei-Chung Lin,et al.  CSG-based object recognition using range images , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[8]  Anil K. Jain,et al.  Recognizing geons from superquadrics fitted to range data , 1992, Image Vis. Comput..

[9]  Robert Bergevin,et al.  Generic object recognition: building coarse 3D descriptions from line drawings , 1989, [1989] Proceedings. Workshop on Interpretation of 3D Scenes.

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

[11]  Frank P. Ferrie,et al.  Darboux Frames, Snakes, and Super-Quadrics: Geometry from the Bottom Up , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Jake K. Aggarwal,et al.  Curvature-based representation of objects from range data , 1986, Image Vis. Comput..

[13]  Ramesh C. Jain,et al.  Segmentation through Variable-Order Surface Fitting , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Anil K. Jain,et al.  On reliable curvature estimation , 1989, CVPR.

[15]  Anil K. Jain,et al.  Segmentation and Classification of Range Images , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Bir Bhanu,et al.  Recognition of 3-D objects in range images using a butterfly multiprocessor , 1989, Pattern Recognit..