Share Email Print

Proceedings Paper

Quantitative analysis of HRR NCTR performance drivers
Author(s): David Iny; Martin M. Morici
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Over the past several years Northrop Grumman has been developing Non-Cooperative Target Recognition (NCTR) technology using High Range Resolution (HRR) Radar data. Common to all NCTR efforts is the need to train classifier algorithms on limited sources of data. The classifier design must also address signature variations with aspect viewing angles and stores configurations. This paper will provide a methodology for quantifying training data segmentation issues including: (1) Degradation due to limited samples within an aspect zone; (2) Stability of scattering centers as a function of aspect angle; and (3) Stores variations. In a program supported by Wright Patterson AFB, Northrop Grumman has developed a detailed statistical model of the Airborne Radar Target Identification HRR signature data. The statistical model is based on a template alignment procedure. This model provides an analytic basis for predicting classifier performance using an associated distance metric. This paper will provide a brief discussion of our template classifier and apply the analytic model to the segmentation issues in the previous paragraph.

Paper Details

Date Published: 17 June 1996
PDF: 9 pages
Proc. SPIE 2747, Radar Sensor Technology, (17 June 1996); doi: 10.1117/12.243073
Show Author Affiliations
David Iny, Northrop Grumman Corp. (United States)
Martin M. Morici, Northrop Grumman Corp. (United States)

Published in SPIE Proceedings Vol. 2747:
Radar Sensor Technology
Gerald S. Ustach, Editor(s)

© SPIE. Terms of Use
Back to Top