Abstract
This article presents the notion of qualitative descriptor, a theoretical tool which describes within the same formalism different approaches to transform quantitative data into qualitative data. This formalism is used with a grouping algorithm to extract qualitative phases from a data flow. Work on action perception, based on qualitative descriptors, is used to illustrate these ideas. The grouping algorithm generates a qualitative symbolic data flow from a video sequence. The ultimate aim is to provide an unsupervised learning algorithm working this qualitative flow to extract abstract description for common actions such as “take”, “push” and “pull”.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
A. Bijaoui. Image et information: introduction au traitement numérique des images. Masson, 1981.
J. Aloimonos, A. Basu, and C. M. Brown. Contour, orientation and motion. In L. S. Baumann, editor, Proceedings: Image Understanding Workshop (Miami Beach, FL, December 9–10, 1985), pages 129–136, San Mateo, CA, 1985. Defense Advanced Research Projects Agency, Morgan Kaufmann.
J. Aloimonos, I. Weiss, and A. Bandyopadhyay. Active vision. International Journal of Computer Vision, 1:333–356, 1988.
Baillie J.-C. and Ganascia J.-G. Segmentation qualitative sur des series de donnees. Actes de CAP’99, Conference d’apprentissage, pages 1–8, 1999.
R. Mann, A. Jepson, and J.M. Siskind. The computational perception of scene dynamics. CVIU, 65(2):113–128, February 1997.
Hirochika Inoue Yasuo Kuniyoshi. Qualitative recognition of ongoing human action sequences. Robotics and vision, pages 1600–1609, 1993.
J.M. Siskind and Q. Morris. A maximum-likelihood approach to visual event classification. In ECCV96, pages II:347–360, 1996.
Rolland P.-Y. and Ganascia J.-G. Flexible mining of patterns in sequential data (à paraitre). ICAI99, 1999.
Rolland P.-Y. and Ganascia J.-G. Flexpat: a novel algorithm for musical pattern discovery. Proceedings of the 12th Colloquium on Musical Informatics, pages 125–128, 1998.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Baillie, JC., Ganascia, JG. (2000). Qualitative Descriptors and Action Perception. In: Hamilton, H.J. (eds) Advances in Artificial Intelligence. Canadian AI 2000. Lecture Notes in Computer Science(), vol 1822. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45486-1_26
Download citation
DOI: https://doi.org/10.1007/3-540-45486-1_26
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67557-0
Online ISBN: 978-3-540-45486-1
eBook Packages: Springer Book Archive