Minimum cost aspect classification: a module of a vision algorithm compiler

The authors present the design of a vision algorithm compiler module for object localization that is used to construct efficient vision programs for a subtask of object localization called aspect classification. Intuitively, an aspect is a representative appearance, and can be associated with a range of viewing positions. In object localization, an object is first classified into an aspect in order to obtain a rough estimate of an object's configuration; this is followed by a numerical minimization procedure to locate the object precisely. The compiler module generates an optimal strategy for aspect classification, in the sense that the average cost of classification is minimal. The performance of the module is illustrated with several examples.<<ETX>>

[1]  K. Ikeuchi,et al.  Determining linear shape change: toward automatic generation of object recognition programs , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

[3]  Yoshiaki Shirai,et al.  An Object Recognition System Using Three-Dimensional Information1 , 1987 .

[4]  Manfredo P. do Carmo,et al.  Differential geometry of curves and surfaces , 1976 .

[5]  W. A. Perkins.  Model-Based Vision System for Scenes Containing Multiple Parts , 1977, IJCAI.

[6]  Lawrence G. Roberts,et al.  Machine Perception of Three-Dimensional Solids , 1963, Outstanding Dissertations in the Computer Sciences.

[7]  Takeo Kanade,et al.  Modelling sensors: Toward automatic generation of object recognition program , 1989, Comput. Vis. Graph. Image Process..

[8]  Chris Goad,et al.  Special purpose automatic programming for 3D model-based vision , 1987 .

[9]  H. Piaggio.  Differential Geometry of Curves and Surfaces , 1952, Nature.

[10]  Rodney A. Brooks,et al.  Symbolic Reasoning Among 3-D Models and 2-D Images , 1981, Artif. Intell..

[11]  R. Bolles,et al.  Recognizing and Locating Partially Visible Objects: The Local-Feature-Focus Method , 1982 .

[12]  Peter B. Scott.  The Australian Robot Marketplace - A Comprehensive Independent Guide to Robots in Austalia Report from Michael Kassler and Associates (Consultants in Computing and Communications), 1984, 119 pp. (£230) , 1986, Robotica.

[13]  W. Grimson,et al.  Model-Based Recognition and Localization from Sparse Range or Tactile Data , 1984 .

[14]  Jesfis Peral,et al.  Heuristics -- intelligent search strategies for computer problem solving , 1984 .

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

[16]  P. Besl.  Geometric modeling and computer vision , 1988, Proc. IEEE.

[17]  Robert C. Bolles,et al.  Locating Partially Visible Objects: The Local Feature Focus Method , 1980, AAAI.

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

[19]  Berthold K. P. Horn,et al.  Determining Grasp Points Using Photometric Stereo and the PRISM Binocular Stereo System , 1984 .

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