Some Problems with Correspondence

  • Michael Jenkin
  • Paul A. Kolers
Part of the The Kluwer International Series in Engineering and Computer Science book series (SECS, volume 44)

Abstract

The notion of correspondence underlies many current theories of human and machine visual information processing. Algorithms for both the correspondence process and solutions to the correspondence problem have appeared regularly in the computer vision literature. Algorithms for stereopsis (Marr and Poggio, 1977; Barnard and Thompson, 1980; Mayhew and Frisby, 1980) and for tracking objects through time (Moravec, 1977; Ullman, 1979; Dreschler and Nagel, 1981; Webb, 1981; Jain and Sethi, 1984) have been presented which assume that token matching of separated or successive views is the underlying visual process. This paper will address the notion of token matching as a primitive operation in vision. We will argue that correspondence seems ill suited to the task of accounting for how an object is positioned in time or space, and that some other mechanism may provide a more apt account.

Keywords

Borate Tral 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Barnard, S. and Thompson, W., (1980) ‘Disparity analysis of images,’ IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-2, no. 4.Google Scholar
  2. Cohen, M.A., and Grossberg, S., (1984) ‘Some global properties of binocular resonances: Disparity matching, filling-in, and figure-ground synthesis,’ Figural Synthesis, P. Dodwell and T. Caelli (eds. ), Lawrence Erlbaum Associates.Google Scholar
  3. Dreschler, L., and Nagel, H.-H., (1981) ‘On the frame-to-frame correspondence between greyvalue characteristics in the images of moving objects,’ Proc. Int. Joint Conf. on Artificial Intelligence, Vancouver, Canada.Google Scholar
  4. Exner, S., (1875) ‘Ueber das sehen von bewegungen und die theorie des zusammengesetzen auges,’ Sitzungsberichte Akademie Wissenchaft, vol. 72, pp. 156–190.Google Scholar
  5. Gescheider, G.A., (1984) Psychophysics: Method, Theory, and Application, Erlbaum, Hillsdale, NJ.Google Scholar
  6. Hoffman, D., and Flinchbaugh, B., (1980) ‘The interpretation of biological motion,’ AI Memo no. 608, MIT.Google Scholar
  7. Jain, R., and Sethi, I., (1984) ‘Establishing correspondence of non-rigid objects using smoothness of motion,’ Proc. 2nd IEEE Workshop on Computer Vision: Representation and Control, Annapolis, MD, pp. 83–37.Google Scholar
  8. Jenkin, M., (1983) ‘Tracking three-dimensional moving light displays,’ ACM Interdisciplinary Workshop on Motion: Representation and Perception, Toronto, Canada.Google Scholar
  9. Julesz, B., (1971) Foundations of Cyclopean Perception, Bell Labs. Inc.Google Scholar
  10. Kolers, P.A., (1968) ‘Some psychological aspects of pattern recognition,’ in Recognizing Patterns, P.A. Kolers, and M. Eden (eds.), MIT Press, Cambridge, MA.Google Scholar
  11. Kolers, P.A., (1972) Aspects of Motion Perception, Pergamon Press Ltd., Headington Hill Hall, Oxford.Google Scholar
  12. Kolers, P.A., (1976) ‘Buswell’s discoveries,’ in Eye Movements and Psychological Processes, R.A. Monty, and J.W. Senders (eds.), Erlbaum, Hillsdale, NJ.Google Scholar
  13. Kolers, P.A., (1983) ‘Some features of visual form,’ Computer Vision,Graphics,and Image Processing, vol. 23, pp. 15–41.CrossRefGoogle Scholar
  14. Kolers, P.A., and Brewster, J.M., (1985) ‘Rhythms and responses,’ J. of Experimental Psychology: Human Perception and Performance, vol. 11, pp. 150–167.CrossRefGoogle Scholar
  15. Kolers, P.A., and Pomerantz, J.R., (1971) ‘Figural change in apparent motion,’ J. of Experimental Psychology, vol. 87, pp. 99–108.CrossRefGoogle Scholar
  16. Marr, D, (1982) Vision, Freeman Press.Google Scholar
  17. Marr, D., and Poggio, T., (1976) ‘Co-operative computation of stereo disparity,’ Science, vol. 194, pp. 283–287.CrossRefGoogle Scholar
  18. Marr, D., and Poggio, T., (1977) ‘A theory of human stereo vision,’ AI Memo, no. 451, MIT.Google Scholar
  19. Mayhew, J., (1983) ‘Models of stereopsis,’ Preliminary Proc. Workshop on Vision,Brain and Cooperative Computation, University of Massachusetts.Google Scholar
  20. Mayhew, J., and Frisby, J., (1980) ‘The computation of binocular edges,’ Perception, vol. 9, pp. 69–86.CrossRefGoogle Scholar
  21. Moravec, H., (1977) ‘Towards automatic visual obstacle avoidance,’ Proc. Intl. Joint Conf. on Artificial Intelligence, Cambridge, MA, p. 54.Google Scholar
  22. Nagel, H.-H., (1982) ‘On change detection and displacement estimation in image sequences,’ Pattern Recognition Letters, vol. 1, pp. 55–59.MATHCrossRefGoogle Scholar
  23. Poggio, G., and Poggio, T., (1984) ‘The analysis of stereopsis,’ Annual Rev. Neuroscience, pp. 379–412.Google Scholar
  24. Ramachandran, V.S., and Anstis, S.M., (1983) ‘Extrapolation of motion path in human visual perception,’ Vision Research, vol. 23, pp. 83–85.CrossRefGoogle Scholar
  25. Rashid, R., (1980) ‘Towards a system for the interpretation of moving light displays,’ IEEE Pattern Analysis and Machine Intelligence, PAMI-2, pp. 574–581.Google Scholar
  26. Terzopoulos, D., (1982) ‘Multi-level reconstruction of visual surfaces: Variational principles and Finite element representations,’ AI Memo, no. 671, MIT.Google Scholar
  27. Thorpe, C.E., (1984) ‘An analysis of interest operators for FIDO,’ Proc. 2nd IEEE Workshop on Computer Vision: Representation and Control, Annapolis, MD.Google Scholar
  28. Ullman, S., (1979) The Interpretation of Visual Motion, MIT Press, Cambridge, MA.Google Scholar
  29. Webb, J., (1981) ‘Structure from motion of rigid and jointed objects,’ Proc. Intl. Joint Conf. on Artificial Intelligence, Vancouver, Canada.Google Scholar

Copyright information

© Kluwer Academic Publishers 1988

Authors and Affiliations

  • Michael Jenkin
  • Paul A. Kolers

There are no affiliations available

Personalised recommendations