Advertisement

A Graph-Theoretic Approach to 3-D Object Recognition and Estimation of Position and Orientation

  • E. K. Wong
  • K. S. Fu

Abstract

This paper describes a new technique for modeling and recognition of 3-D objects. 3-D objects are modeled as graphs where the nodes correspond to object vertices and the branches correspond to object edges. Allowable junction types at each object vertex are assigned as the property at the corresponding node of the model graph. Allowable junction type combinations of the neighboring vertices at a given vertex are established as contraints required at the corresponding node of the model graph. The 2-D projections of an object are modeled as subgraph isomorphisms of the model graph. Recognition is by searching if a 2-D projection graph is a subgraph isomorphism of the model graph, and each node in the projection graph also satisfies the constraints at the node of the model graph matched. Techniques are described for the estimation of position and orientation of a 3-D object based on the proposed scheme. Experiments are conducted to evaluate the performance.

Keywords

Object Recognition Model Graph Neighboring Node Line Drawing Subgraph Isomorphism 
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]
    K. Fukunaga, Introduction to Statistical Pattern Recognition, Academic Press, New York, 1972.Google Scholar
  2. [2]
    K. S. Fu, Syntactic Pattern Recognition and Applications, Prentice Hall, New Jersey, 1982.MATHGoogle Scholar
  3. [3]
    W. A. Perkins, “A model-based vision system for industrial parts,” IEEE Trans. on Computers, C-27, (2), pp. 126–143, February 1978.Google Scholar
  4. [4]
    S. W. Holland, L. Rossol, and W. R. Ward, “CONSIGHT-1: A Vision Controlled Robot System for Transferring Parts from Belt Conveyors,” Computer Vision and Sensor Based Robots, edited by G. C. Dodd and L. Rossol, Plenum Press, New York, 1979.Google Scholar
  5. [5]
    I. Chakravarty and H. Freeman, “Characteristic views as a basis for three-dimensional object recognition,” SPIE Vol. 336 Robot Vision, pp. 37–45, 1982.Google Scholar
  6. [6]
    N. Chen, J. Birk, and R. Kelly, “Estimating workpiece pose using the feature point method,” IEEE Trans. on Automatic Control, AC-25, (6), December 1980.Google Scholar
  7. [7]
    R. A. Brooks, “Symbolic reasoning among 3-D models,” Artificial Intelligence, Vol. 17, pp. 285–348, August 1981.CrossRefGoogle Scholar
  8. [8]
    D. Marr and H. K. Nishihara, “Representation and recognition of the spatial organization of three-dimensional shapes,” MIT A.I. Laboratory Memo 377, August 1976.Google Scholar
  9. [9]
    L. G. Shapiro, R. M. Haralick, J. D. Moriarty, and P. G. Mulgaonkar, “Matching three-dimensional models,” Proc. IEEE Computer Society Conference on PRIP, Dallas, TX, pp. 534–541, August 1981.Google Scholar
  10. [10]
    H. G. Barrow and J. M. Tennenbaum, “Interpreting line drawing as three-dimensional surfaces,” Artificial Intelligence, Vol. 17, pp. 75–116, August 1981.CrossRefGoogle Scholar
  11. [11]
    S. E. Yam, “Three-dimensional pattern analysis for industrial robotic systems,” Ph.D. thesis, School of Electrical Engineering, Purdue University, August 1976.Google Scholar
  12. [12]
    A. A. G. Requicha, “Representation for rigid solids: Theory, methods, and systems,” Computing Surveys, Vol. 12, No. 4, December 1980.Google Scholar
  13. [13]
    L. G. Roberts, “Machine Perception of Three-Dimensional Solids,” in J. Tipett (ed.), Optical and Electro-Optical Information Processing, Cambridge, MA: MIT Press, pp. 159–197, 1965.Google Scholar
  14. [14]
    R. Shapira, “Computers reconstruction of bodies bounded by quadric surfaces from a set of imperfect projections,” Tech. Rep. CRL-48, Rensselaer Polytechnic Inst., Troy, NY, 1976.Google Scholar
  15. [15]
    I. Chakravarty, “A generalized line and junction labelling scheme with application to scene analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-1, (2), April 1979.Google Scholar
  16. [16]
    R. Nevatia, Machine Perception, Prentice-Hall, Inc., New Jersey, 1982.Google Scholar
  17. [17]
    W. K. Giloi, Interactive Computer Graphics, Prentice-Hall, New Jersey, 1978.Google Scholar
  18. [18]
    J. A. Bondy and U. S. R. Murty, Graph Theory with Applications, North Holland, Inc., 1981.Google Scholar
  19. [19]
    M. B. Clowes, “On seeing things,” Artificial Intelligence, Vol. 1, pp. 79–116, 1970.Google Scholar
  20. [20]
    D. A. Huffman, “Impossible Objects as Nonsense Sentences,” in Machine Intelligence, Vol. 6, B. Meltzer and D. Michie, Ed., American Elsevier, New York, pp. 295–323, 1971.Google Scholar
  21. [21]
    I. Sobel, “On calibrating computer controlled cameras for perceiving 3-D scenes,” Artificial Intelligence, Vol. 5, No. 2, 1974.Google Scholar
  22. [22]
    D. B. Gennery, “Modelling the environment of an exploring vehicle by means of stereo vision,” Stanford Artificial Intelligence Laboratory Memo AIM-339 (Ph.D. thesis), June 1980.Google Scholar
  23. [23]
    M. A. Fischler and R. C. Bolles, “Random samples consensus: A paradigm for model filtering with applications to image analysis and automated cartography,” Communications of the ACM, Vol. 24, No. 6, pp. 381–396, June 1981.MathSciNetCrossRefGoogle Scholar

Copyright information

© Plenum Press, New York 1985

Authors and Affiliations

  • E. K. Wong
    • 1
  • K. S. Fu
    • 1
  1. 1.School of Electrical EngineeringPurdue UniversityWest LafayetteUSA

Personalised recommendations