Spherical Representations: for EGI to SAI

One of the fundamental problems in representing a curved surface is how to define an intrinsic, i.e., viewer independent, coordinate system over the surface. More precisely, in order to establish point matching between model and observed feature distributions over curved surfaces, we need to set up a coordinate system that maps a point on a curved surface to a point on a standard coordinate system. This mapping should be independent of the viewing direction. Since the boundary of a 3-D object forms a closed surface, a coordinate system defined on the sphere is preferred. We have been exploring several intrinsic mappings from an object surface to a spherical surface. We have investigated several representations including: the EGI (Extended Gaussian Image), the DEGI (Distributed Extended Gaussian Image), the CEGI (Complex Extended Gaussian Image), and the SAI (Spherical Attribute Image). This paper describes each representation and the lessons that we have learned by using those representations in recognition systems.

[1]  C. Gauss,et al.  General investigations of curved surfaces , 1902 .

[2]  M. Hebert,et al.  Merging multiple views using a spherical representation , 1994, Proceedings of 1994 IEEE 2nd CAD-Based Vision Workshop.

[3]  M. Hebert,et al.  The Representation, Recognition, and Locating of 3-D Objects , 1986 .

[4]  Philip E. Brou.  Using the Gaussian Image to Find the Orientation of Objects , 1984 .

[5]  Berthold K. P. Horn.  Extended Gaussian images , 1984, Proceedings of the IEEE.

[6]  Katsushi Ikeuchi,et al.  Picking up an Object from a Pile of Objects. , 1983 .

[7]  Katsushi Ikeuchi.  Recognition of 3-D Objects Using the Extended Gaussian Image , 1981, IJCAI.

[8]  Takeo Kanade,et al.  Three-Dimensional Machine Vision , 1987 .

[9]  L. A. Li︠u︡sternik.  Convex figures and polyhedra , 1966 .

[10]  Robert C. Bolles,et al.  3DPO: A Three- Dimensional Part Orientation System , 1986, IJCAI.

[11]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Katsushi Ikeuchi,et al.  A spherical representation for the recognition of curved objects , 1993, 1993 (4th) International Conference on Computer Vision.

[13]  Charles R. Dyer,et al.  Model-based recognition in robot vision , 1986, CSUR.

[14]  Gérard G. Medioni,et al.  Structural Indexing: Efficient 3-D Object Recognition , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Jean Ponce,et al.  Describing surfaces , 1985, Comput. Vis. Graph. Image Process..

[16]  Kevin W. Bowyer,et al.  Aspect graphs: An introduction and survey of recent results , 1990, Int. J. Imaging Syst. Technol..

[17]  Katsushi Ikeuchi,et al.  The Complex EGI: A New Representation for 3-D Pose Determination , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  John W. Roach,et al.  Spherical dual images: A 3D representation method for solid objects that combines dual space and Gaussian spheres , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[19]  Yoshiaki Shirai,et al.  Object Recognition Using Three-Dimensional Information , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  James J. Little.  Determining Object Attitude from Extended Gaussian Images , 1985, IJCAI.