Compatibilities for the Perception-Action Cycle

  • Josef Pauli
  • Gerald Sommer
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1998)


We apply an eye-on-hand Robot Vision system for treating the following three tasks: (a) Tracking objects for obstacle avoidance; (b) Arranging certain viewing conditions; (c) Acquiring an object recognition function. The novelty is the use of so-called compatibilities between motion features and view sequence features. Under real image formation, compatibilities are more general and appropriate than exact invariants. We demonstrate the usefulness for constraining the search for corresponding features, for parameterizing correlation matching procedures, and for fine-tuning approximations of appearance manifolds.


Motion Vector Training Image Obstacle Avoidance Edge Orientation Robot Vision 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Y. Aloimonos, C. Fermüller: Analyzing action representations. Workshop on Algebraic Frames for the Perception-Action Cycle, LNCS 1888 (2000) 1–21. 227Google Scholar
  2. 2.
    S. Becker: Implicit learning in 3D object recognition-The importance of temporal context. Neural Computation 11 (1999) 347–374. 232CrossRefGoogle Scholar
  3. 3.
    T. Binford, T. Levitt: Quasi-invariants-Theory and exploitation. Image Understanding Workshop (1993) 819–829. 227Google Scholar
  4. 4.
    M. Bolduc, M. Levine: A review of biologically motivated space-variant data reduction models for robot vision. Comp. Vis. and Image Understanding 69 (1998) 170–184. 229CrossRefGoogle Scholar
  5. 5.
    H. Murase, S. Nayar: Visual learning and recognition of 3D objects from appearance. Internat. J. of Computer Vision 14 (1995) 5–24. 231CrossRefGoogle Scholar
  6. 6.
    J. Pauli: Compatibilities for boundary extraction, Symp. der Deutschen Arbeitsgem. für Mustererkennung, Informatik aktuell, Springer-Verlag (2000) 468–475. 235Google Scholar
  7. 7.
    S. Smith, J. Brady: SUSAN-A new approach to low level image processing. Internat. J. of Computer Vision 23 (1997) 45–78. 228CrossRefGoogle Scholar
  8. 8.
    R. Szeliski, D. Tonnesen: Surface modeling with oriented particle systems. ACM SIGGRAPH Computer Graphics Annual Conf. (1992) 185–194. 233Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Josef Pauli
    • 1
  • Gerald Sommer
    • 1
  1. 1.Institut für Informatik und Praktische MathematikChristian-Albrechts-Universität zu KielKielGermany

Personalised recommendations