Machine learning for extracting target electrical parameters from qualitative inverse scattering imagery

Matthew J. Burfeindt; Hatim F. Alqadah

doi:10.1117/12.2551880

23 April 2020 Machine learning for extracting target electrical parameters from qualitative inverse scattering imagery

Proceedings Volume 11408, Radar Sensor Technology XXIV; 1140802 (2020) https://doi.org/10.1117/12.2551880
Event: SPIE Defense + Commercial Sensing, 2020, Online Only

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.

Conference Presentation

Citation Download Citation

Matthew J. Burfeindt and Hatim F. Alqadah "Machine learning for extracting target electrical parameters from qualitative inverse scattering imagery", Proc. SPIE 11408, Radar Sensor Technology XXIV, 1140802 (23 April 2020); https://doi.org/10.1117/12.2551880

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available