ADAM Neural Networks for Parallel Vision

This paper describes current research on neural networks within the collaborative project "Vision by Associative Reasoning" 1. The major aim of the work is the matching of vector descriptions of maps to airbourne IR imagery. The primary application of the work is in the guidance of airbourne vehicles. The paper describes how neural networks are being used to identify urban and field areas and for road network extraction. It goes on to show how the work is developing architectures that use neural associative memories to process visual information. It presents a brief review of the project's aims' and current approach and the work of each of the partners.