Viewer Independent Shape Recognition

An important problem in vision is to detect the presence of a known rigid 3-D object. The general 3-D object recognition task can be thought of as building a description of the object that must have at least two parts: 1) the internal description of the object itself (with respect to an object-centered frame); and 2) the transformation of the object-centered frame to the viewer-centered (image) frame. The reason for this decomposition is parsimony: different views of the object should have minimal impact on its description. This is achieved by factoring the object's description into two sets of parameters, one which is view-independent (the object-centered component) and one which is view-varying (the viewing transformation). Often a description of the object is known beforehand and the task reduces to finding the objectframe to viewer-frame transformation. This paper describes a method for handling this case: a known object is detected by finding changes in orientation, translation, and scale of the object from its canonical description. The method is a Hough technique and has the characteristic insensitivity to occlusion and noise.

[1]  D. Ballard,et al.  Experience with the Generalized Hough Transform , 1980 .

[2]  David Marr,et al.  Representing Visual Information , 1977 .

[3]  Geoffrey E. Hinton.  Some Demonstrations of the Effects of Structural Descriptions in Mental Imagery , 1979, Cogn. Sci..

[4]  Geoffrey E. Hinton.  Some Demonstrations of the Effects of Structural Descriptions in Mental Imagery , 1979, Cogn. Sci..

[5]  Bruce G. Baumgart.  Winged edge polyhedron representation. , 1972 .

[6]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[7]  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.

[8]  Dana H. Ballard,et al.  Rigid body motion from depth and optical flow , 1983, Comput. Vis. Graph. Image Process..

[9]  Dana H. Ballard,et al.  On Shapes , 1981, International Joint Conference on Artificial Intelligence.

[10]  Gerald J. Agin.  Representation and description of curved objects , 1972 .

[11]  Tomaso Poggio,et al.  A Theory of Human Stereo Vision , 1977 .

[12]  Irvin Rock,et al.  Orientation and form , 1974 .

[13]  Takeo Kanade,et al.  Recovery of the Three-Dimensional Shape of an Object from a Single View , 1981, Artif. Intell..

[14]  Christopher M. Brown,et al.  Some Mathematical and Representational Aspects of Solid Modeling , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Jerome A. Feldman,et al.  Computing with Connections , 1981 .

[16]  Kokichi Sugihara,et al.  Range-Data Analysis Guided by a Junction Dictionary , 1979, Artif. Intell..

[17]  Thomas O. Binford,et al.  Computer Description of Curved Objects , 1973, IEEE Transactions on Computers.

[18]  Jerome A. Feldman,et al.  Connectionist Models and Their Properties , 1982, Cogn. Sci..

[19]  H. Barrow,et al.  RECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES , 1978 .

[20]  K. Ikeuchi.  Numerical Shape from Shading and Occluding Contours in a Single View , 1979 .

[21]  Dana H. Ballard,et al.  Parameter Networks: Towards a Theory of Low-Level Vision , 1981, IJCAI.

[22]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[23]  Geoffrey E. Hinton.  Shape Representation in Parallel Systems , 1981, IJCAI.