Visual Form pp 479-493 | Cite as

View-Class Representation and Matching of 3D Objects

  • Linda G. Shapiro

Abstract

Three-dimensional object recognition is difficult because an object looks different when viewed from different viewpoints. One solution to this problem is to represent the 3D object as a set of 2D models, one for each of a set of view classes. A view class is a set of viewpoints that all produce images with the same or similar features. View-class matching consists of determining the correspondence between the features extracted from an image of an unknown object and the features of a particular view class of a particular object model. View-class matching is used in object recognition, pose estimation, and inspection systems.

Keywords

Line Segment Line Drawing Vision Model View Class Template Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Buchanan, C. G., “Determining Surface Orientation from Specular Highlights”, M.S. thesis, Computer Science Department, University of Toronto, 1986.Google Scholar
  2. 2.
    Camps, O. I., L. G. Shapiro, and R. M. Haralick, “PREMIO: An Overview”, Proceedings of the IEEE Workshop on Automated CAD-Based Vision, June, 1991.Google Scholar
  3. 3.
    Chakravarty, I. and H. Freeman, “Characteristic Views as a Basis for Three-Dimensional Object Recognition”, Proceedings of SPIE 336 (Robot Vision), 1982, pp. 37-45.Google Scholar
  4. 4.
    Cook, R. L., and K. E. Torrance, “A reflectance Model for Computer Graphics”, ACM Transactions on Graphics, Vol. 1, 1982, pp. 7–24.CrossRefGoogle Scholar
  5. 5.
    Goad, C., “Special Purpose, Automatic Programming for 3D Model-Based Vision”, DARPA Image Understanding Workshop, 1983, pp. 94-104.Google Scholar
  6. 6.
    Hansen, C. and T. Henderson, “Toward the Automatic Generation of Recognition Strategies”, Proceedings of the 2nd International Conference on Computer Vision, 1988, pp. 275-279.Google Scholar
  7. 7.
    Haralick, R. M. and L. G. Shapiro, “The Consistent Labeling Problem: Part I”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 1, No. 2, 1979, pp. 173–184.MATHCrossRefGoogle Scholar
  8. 8.
    Henikoff, J. and L. G. Shapiro, “Interesting Patterns for Model-Based Vision”, Proceedings of the 3rd International Conference on Computer Vison, 1990, pp. 535-538.Google Scholar
  9. 9.
    Ikeuchi, K., “Generating an Interpretation Tree from a CAD Model for 3D-Object Recognition in Bin-Picking Tasks”, International Journal of Computer Vision, Vol. 2, 1987, pp. 145–165.CrossRefGoogle Scholar
  10. 10.
    Lowe, D. G., “Three-Dimensional Object Recognition from Single Two-Dimensional Images”, Artificial Intelligence, Vol. 31, 1987, pp. 355–395.CrossRefGoogle Scholar
  11. 11.
    Mohan, R. and R. Nevatia, “Using Perceptual Organization to Extract 3D Structures”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 11, No. 11, 1989, pp. 1121–1139.CrossRefGoogle Scholar
  12. 12.
    Ponce, J. and D. Chelberg, “Finding the limbs and Cusps of Generalized Cylinders”, International Journal of Computer Vision, Vol. 3, 1987, pp. 195–210.Google Scholar
  13. 13.
    Shapiro, L. G. and H. Lu, “Accumulator-Based Inexact Matching Using Relational Summaries”, Machine Vision and Applications, Vol 3, 1990, pp. 143–158.CrossRefGoogle Scholar
  14. 14.
    Yi, S., R. M. Haralick, and L. G. Shapiro, “Automatic Sensor and Light Source Positioning for Machine Vision”, Proceedings of the 10th International Conference on Pattern Recognition, June, 1990, pp. 55-59.Google Scholar

Copyright information

© Springer Science+Business Media New York 1992

Authors and Affiliations

  • Linda G. Shapiro
    • 1
  1. 1.Department of Computer Science and Engineering, FR-35University of WashingtonSeattleUSA

Personalised recommendations