Domain fusion based feature extraction for SAR ATR

Terell L. Dale, Ngoc B. Tran, Ram M. Narayanan, Ramesh Bharadwaj

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The all-weather and light condition operability of synthetic aperture radar (SAR) imaging systems makes them the optimal choice for several civilian and military remote sensing applications. Deep learning methods have demonstrated state-ofthe-art classification performance on standard SAR datasets such as the Moving and Stationary Target Acquisition and Recognition (MSTAR) Standard Operating Conditions (SOC) 10-target dataset. However, high acquisition costs limit the availability SAR domain data, both in number and diversity for use in training neural networks. This in turn limits the performance of these networks when used to classify SAR images acquired using radar system specifications and imaging environments that differ from the specifications used to create the images used for training. In this work, Siamese Networks, made up of twin AlexNet-based CNNs, were trained using subsets of the Military Ground Target Dataset (MGTD) and MSTAR datasets to learn radar specification and imaging environment invariant features thereby increasing the classification performance on the MGTD test set by 4.17%.

Original languageEnglish (US)
Title of host publicationRadar Sensor Technology XXVI
EditorsKenneth I. Ranney, Ann M. Raynal
PublisherSPIE
ISBN (Electronic)9781510650923
DOIs
StatePublished - 2022
EventRadar Sensor Technology XXVI 2022 - Virtual, Online
Duration: Jun 6 2022Jun 12 2022

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume12108
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceRadar Sensor Technology XXVI 2022
CityVirtual, Online
Period6/6/226/12/22

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Domain fusion based feature extraction for SAR ATR'. Together they form a unique fingerprint.

Cite this