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.

Radar Automatic Target Recognition (ATR) and NonCooperative Target Recognition (NCTR) captures material presented by leading international experts at a NATO lecture series and explores both the fundamentals of classification techniques applied to data from a variety of radar modes and selected advanced techniques at the forefront of research. The ability to detect and locate targets by day or night, over wide areas, regardless of weather conditions has long made radar a key sensor in many military and civil applications. However, the ability to automatically and reliably distinguish different targets represents a difficult challenge, although steady progress has been made over the past couple of decades. This book explores both the fundamentals of classification techniques applied to data from a variety of radar modes and selected advanced techniques at the forefront of research. Topics include: the problem as applied to the ground, air and maritime domains; impact of image quality on the overall target recognition performance; performance of different approaches to the classifier algorithm; improvement in performance to be gained when a target can be viewed from more than one perspective; ways in which natural systems perform target recognition; impact of compressive sensing; advances in change detection, including coherent change detection; and challenges and directions for future research.

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.