Visual Knowledge Representation of Moving Scenes

A. Chella1, M. Frixione2, S. Gaglio1 

1Dipartimento di Ingeneria Automatica e Informatica, University of Palermo, and CERE-CNR, Vialle delle Scienze, I-90128 Palermo, Italy
2Dipartimento di Scienze della Comunicazione, University of Salerno, Via Ponte Don Melillo, I-84084 Fisciano (Salerno), Italy

Abstract

We describe a framework for the representation of visual knowledge, with particular attention to the analysis and the representation of scenes with moving persons and objects. Our aim is to integrate in a principled way the models developed within the artificial vision community and the propositional knowledge representation systems developed within symbolic AI. We claim that this integration requires the introduction of a missing link between these two classes of representations. In our model, such a role is played by the notion of conceptual space (CS), a representation in which information is characterized in terms of a metric space. We illustrate our proposal by referring to an experimental set-up, based on a vision system that takes in input real images of moving people.

Keywords

perception, artificial vision, knowledge representation, conceptual spaces, action representation, hybrid models