Abstract
“Scene Analysis”, especially for real data, is a complex problem. There are two main explanations which interest us in this paper.
The first one is that sometimes an object identification needs informations about his spatial context ([GAR76,OHTA89]). We define the spatial context of an object as topological relations beetween this object and the other objects of the world.
The second explanation is that the detection of an object implies to solve simultaneously two problems, the localization and the identification. This is really difficult because sometimes for the same object class, we must consider variations, for instance shape variation or colour variation. To solve these problems, we use generic models of objects [FUA87,GAR89] which can be expensive with computing time if they explore the whole scene.
In this paper, we increase the formalization of spatial context and we show how it allows to focus the search objects in a limited aera of the scene.
Chapter PDF
Keywords
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.
References
J.L ANTOINE, O. CORBY, M. PUGGELI: “ERASME, a multi expert system for pavement rehabilitation” International Conference on Applications of Advanced Technologies in Transportation Engineering, San Diego, February 89.
J. FAIRFIELD: “An Algorithm of diffusion” Rapport de Recherche INRIA à paraître.
P. FUA, A.J. HANSON: ” Using geometric models for intelligent Shape extraction”, Image Understanding Workshop, February 87.
T.D. GARVEY: “Perceptual strategies for purposive vision”. Tech. Note 117. Menlo Park, Calif.: SRI Artificial Intelligence Center.
P. GARNESSON, G. GIRAUDON, P. MONTESINOS: “MESSIE: application à l'interprétation en imagerie aerienne” Rapport de Recherche INRIA n 1012, Mars 89.
P. GARNESSON, P. MONTESINOS, G. GIRAUDON, ”MESSIE: Un système multi spécialiste en vision” 7ème congrès Reconnaissance des formes et Intelligence Artificielle, AFCET Novembre 89.
B. HAYES-ROTH: ” The Blackboard Architecture: A General Framework for Problem Solving ?”, Stanford University, Report HPP-83-30, May 83
H. LAASRI, B. MAITRE: “Coopération dans un univers multi-agents basée sur le modèle du blackboard: études et réalisations”. These, Université de Nancy I, 89.
P. MONTESINOS, G. GIRAUDON, ” A Rule Interpreter for Handling Image Primitives in Scene Analysis”, Rapport de Recherche INRIA, A paraître.
Y. OHTA:”A region oriented image-analysis system by computer” Ph.D. thesis, Kyoto University Department of Information Science.
B.A. DRAPER, R.T. COLLINS, A.R. HANSON, E.M.RISEMAN:” The Schema System”. International Journal of Computer Vision 89.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Garnesson, P., Giraudon, G. (1990). Spatial context in an image analysis system. In: Faugeras, O. (eds) Computer Vision — ECCV 90. ECCV 1990. Lecture Notes in Computer Science, vol 427. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0014912
Download citation
DOI: https://doi.org/10.1007/BFb0014912
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-52522-6
Online ISBN: 978-3-540-47011-3
eBook Packages: Springer Book Archive