Contains the unclassified papers presented at the Symposium. Novel solutions to the Non-Cooperative Target Identification (NCTI) Problem, using radar are proposed. The papers are presented under the following headings: System requirements -- Target characterisation -- Radar measurements and feature extraction -- Target classification -- Scattering techniques, target modelling and validation.

This final report summarizes the accomplishments of the AASERT research supported by the AFOSR Grant F4962O-96-l-O264, entitled, Non-Cooperative Target Recognition. This Grant supported the Ph. D. dissertation of Dr. William Phillips, who after graduation returned to Northrop-Grumman Corporation. He is on leave at DARPA managing a research program on advanced architectures for image and signal processing. This research effort supported the design and analysis of novel algorithms for the exploitation of Synthetic Aperture Radar (SAR) imagery. The algorithms developed under this effort facilitate the monitoring of vehicular activities, which is one of the most important SAR image exploitation problems in military applications. Several of the primary components of an exploitation system to monitor such activities have been addressed, including high-speed target detection using parallel processors, site model construction, site-model based false alarm reduction and change detection. Experiments with TESAR and MSTAR data have been conducted.