Share Email Print

Proceedings Paper

Machine learning for extracting target electrical parameters from qualitative inverse scattering imagery
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The Linear Sampling Method is an imaging technique that reconstructs target shape via a series of beamforming operations without using linear scattering assumptions. The norm of the solution is typically used to determine which pixels are inside the target support. There has not been much study of how to use the phase of the solution to aid in target identification. In this study, we explore using the solution phase to classify targets according to their electrical properties via a machine learning approach. We implement a support vector machine, apply it to imagery from simulated target data, and quantify classification accuracy.

Paper Details

Date Published: 23 April 2020
PDF: 10 pages
Proc. SPIE 11408, Radar Sensor Technology XXIV, 1140802 (23 April 2020);
Show Author Affiliations
Matthew J. Burfeindt, U.S. Naval Research Lab. (United States)
Hatim F. Alqadah, U.S. Naval Research Lab. (United States)

Published in SPIE Proceedings Vol. 11408:
Radar Sensor Technology XXIV
Kenneth I. Ranney; Ann M. Raynal, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?