Image classifier and scene understanding systems of multiagent teams

Abstract

A multiagent architecture for scene understanding systems is described. Such systems consist of a collection of coupled vision sub-systems each one dedicated to a particular sensor. Interaction between the vision sub-systems is controlled by an organising agent. Each vision sub-system is implemented on the basis of a partition tree image labelling representation and an associated multiagent hierarchy of classifiers controlled by an organising agent. Each classifier in the multiagent hierarchy of classifiers may be implemented as a decision tree of neural network classifiers acting on feature vectors derived from regions in the partition tree. Therefore the image labelling and image classific..