Experiments on the use of the ATMS to label features for object recognition

  • R. M. Bodington
  • G. D. Sullivan
  • K. D. Baker
Recognition - Matching
Part of the Lecture Notes in Computer Science book series (LNCS, volume 427)


Experiments are reported on the use of an Assumption-based Truth Maintenance System (ATMS) [6] to establish a match between a 3-d model and a single 2-d image. We show that the ATMS improves the efficiency of the search for maximal combinations of consistently labelled features. A memory cost is incurred, associated with the recording system of the ATMS; this can be reduced by simple heuristics. Empirical evidence is presented quantifying the costs and benefits of the method.


Object Recognition Constraint Evaluation Binary Constraint Consistent Labelling Recording Mechanism 
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.

8. References

  1. [1]
    R.Bodington and P.Elleby "Justification and Assumption-based Truth Maintenance Systems: When and How to use them in Constraint Satisfaction," in Reason Maintenance Systems and their Applications, Ed. B.Smith and G.Kelleher, Ellis Horwood, 1988Google Scholar
  2. [2]
    R.Bodington, G.D.Sullivan and K.D.Baker, "The Consistent Labelling of Image Features using an ATMS", Image Vision & Computing, vol. 7, no. 1, February 1989.Google Scholar
  3. [3]
    R.Bodington, G.D.Sullivan and K.D.Baker, "Experiments on the use of the ATMS to label features for object recognition" University of Reading, unpublished report December 1989Google Scholar
  4. [4]
    K.Brisdon, G.D.Sullivan and K.D.Baker, "Feature Aggregation in Iconic Model Evaluation," Proceedings of the Alvey Vision Conference, AVC88, Sept. 1988.Google Scholar
  5. [5]
    J. Canny, "Finding edges and lines in images.", Ph.D. AI-laboratory, MIT, Cambridge, MA, 1983Google Scholar
  6. [6]
    J.De Kleer "An Assumption-Based TMS", Artificial Intelligence, vol. 28, no. 2, March 1986.Google Scholar
  7. [7]
    J.De Kleer "Extending the ATMS", Artificial Intelligence, vol 28, no. 2, March 1986.Google Scholar
  8. [8]
    C.Goad "Special purpose automatic programming for 3-d model-based vision", Proc. ARPA Image Understanding Workshop, 1983.Google Scholar
  9. [9]
    W. Grimson, and T. Lozano-Pérez, "Model-Based Recognition and Localization from Sparse Range or Tactile Data." A.I. Memo 738, MIT, Cambridge, MA, August 1983.Google Scholar
  10. [10]
    W. Grimson and T. Lozano-Pérez, "Localizing overlapping parts by searching the interpretation tree," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. PAMI-9, no. 4, July 1987.Google Scholar
  11. [11]
    W.Grimson, "The combinatorics of object recognition in cluttered environments using constrained search," 2nd International Conference on Computer Vision, ICCV88, Dec. 1988.Google Scholar
  12. [12]
    D.G.Lowe, "Three-dimensional Object Recognition from Single Two-dimensional Images.," Artificial Intelligence, no. 31, 1987.Google Scholar
  13. [13]
    G.Provan, "Efficiency Analysis of Multiple-Context TMSs in Scene Representation." Proceedings 6th National Conference on Artificial Intelligence, AAAI-87, 1987.Google Scholar
  14. [14]
    A.Rydz, G.D.Sullivan and K.D.Baker, "Model-based Vision Planar Representation of the Viewsphere," Proceedings of the Alvey Vision Conference, AVC88, Sept. 1988.Google Scholar
  15. [15]
    A.Worrall, G.D.Sullivan and K.D.Baker, "Model-based Perspective Inversion," Proceedings of the Alvey Vision Conference, AVC88, Sept. 1988.Google Scholar
  16. [16]
    A.Worrall, G.D.Sullivan and K.D.Baker, "The Roll Angle Consistency Constraint" Proceedings of the Alvey Vision Conference, AVC89, Sept. 1989Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1990

Authors and Affiliations

  • R. M. Bodington
    • 1
  • G. D. Sullivan
    • 2
  • K. D. Baker
    • 2
  1. 1.British AerospaceSowerby Research CentreFilton, BristolUK
  2. 2.Dept. of Computer ScienceUniversity of ReadingReadingUK

Personalised recommendations