Automatic target recognition in SAR images: Comparison between pre-trained CNNs in a tranfer learning based approach

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

20 Scopus citations

Abstract

Synthetic aperture radar (SAR) are high resolution imaging radar systems. In many SAR applications classifying objects that are detected within the SAR image is important. In this paper an approach is proposed to tackle the Synthetic SAR Automatic Target Recognition (ATR) problem. The proposed scheme is based on a transfer leaning approach where three different pre-trained Convolutional Neural Networks (CNNs) are used as feature extractors in combination with a Support Vector Machine classifier (SVM). The CNNs used in this paper are AlexNet, VGG16 and GoogLeNet. The performance of these three CNNs is compared in regards to the SAR-ATR problem; where it is observed that AlexNet gives the best performance accuracy of 99.27%.

Original languageBritish English
Title of host publication2018 International Conference on Artificial Intelligence and Big Data, ICAIBD 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages160-164
Number of pages5
ISBN (Electronic)9781538669877
DOIs
StatePublished - 25 Jun 2018
Event2018 International Conference on Artificial Intelligence and Big Data, ICAIBD 2018 - Chengdu, China
Duration: 26 May 201828 May 2018

Publication series

Name2018 International Conference on Artificial Intelligence and Big Data, ICAIBD 2018

Conference

Conference2018 International Conference on Artificial Intelligence and Big Data, ICAIBD 2018
Country/TerritoryChina
CityChengdu
Period26/05/1828/05/18

Keywords

  • Automatic target recognition
  • Deep learning
  • Synthetic aperture radar
  • Transfer learning

Fingerprint

Dive into the research topics of 'Automatic target recognition in SAR images: Comparison between pre-trained CNNs in a tranfer learning based approach'. Together they form a unique fingerprint.

Cite this