Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Y. Aloimonos, C. Fermüller: Analyzing action representations. Workshop on Algebraic Frames for the Perception-Action Cycle, LNCS 1888 (2000) 1–21. 227
S. Becker: Implicit learning in 3D object recognition-The importance of temporal context. Neural Computation 11 (1999) 347–374. 232
T. Binford, T. Levitt: Quasi-invariants-Theory and exploitation. Image Understanding Workshop (1993) 819–829. 227
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. 229
H. Murase, S. Nayar: Visual learning and recognition of 3D objects from appearance. Internat. J. of Computer Vision 14 (1995) 5–24. 231
J. Pauli: Compatibilities for boundary extraction, Symp. der Deutschen Arbeitsgem. für Mustererkennung, Informatik aktuell, Springer-Verlag (2000) 468–475. 235
S. Smith, J. Brady: SUSAN-A new approach to low level image processing. Internat. J. of Computer Vision 23 (1997) 45–78. 228
R. Szeliski, D. Tonnesen: Surface modeling with oriented particle systems. ACM SIGGRAPH Computer Graphics Annual Conf. (1992) 185–194. 233
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pauli, J., Sommer, G. (2001). Compatibilities for the Perception-Action Cycle. In: Klette, R., Peleg, S., Sommer, G. (eds) Robot Vision. RobVis 2001. Lecture Notes in Computer Science, vol 1998. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44690-7_28
Download citation
DOI: https://doi.org/10.1007/3-540-44690-7_28
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41694-4
Online ISBN: 978-3-540-44690-3
eBook Packages: Springer Book Archive