Share Email Print

Proceedings Paper

Target model generation from multiple SAR images
Author(s): John A. Richards; John W. Fisher III; Alan S. Willsky
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

An important problem driving much research in the SAR and model-based ATR communities is the generation and modification of target models for ATR system databases. We propose a method for generating or updating 3-D reflector primitive target models. We utilize an existing 2-D extraction algorithm to extract feature locations and classifications (such as scattering primitive type) from each image in a set of SAR data. We formulate the 3-D model generation in terms of a data association problem. We present an iterative algorithm, based on the expectation-maximization (EM) method, to solve the data association problem and yield a maximum likelihood estimate of target feature locations and types from the set of 2-D extracted features. Finally, we present examples and results for sets of simulated SAR imagery.

Paper Details

Date Published: 13 August 1999
PDF: 14 pages
Proc. SPIE 3721, Algorithms for Synthetic Aperture Radar Imagery VI, (13 August 1999); doi: 10.1117/12.357675
Show Author Affiliations
John A. Richards, Massachusetts Institute of Technology (United States)
John W. Fisher III, Massachusetts Institute of Technology (United States)
Alan S. Willsky, Massachusetts Institute of Technology (United States)

Published in SPIE Proceedings Vol. 3721:
Algorithms for Synthetic Aperture Radar Imagery VI
Edmund G. Zelnio, Editor(s)

© SPIE. Terms of Use
Back to Top