Ground moving radar targets classification based on spectrogram images using convolutional neural networks

Esra Al Hadhrami, Maha Al Mufti, Bilal Taha, Naoufel Werghi

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

31 Scopus citations

Abstract

In this paper, a new approach for classifying ground moving targets captured by Pulsed Doppler Radars is proposed. Radar echo signals express the doppler effect produced by the movement of targets. Those signals can be processed in different domains to attain distinctive characteristics of targets that can be used for target classification. Our proposed approach is based on utilizing a pre-trained Convolutional Neural Network (CNN), VGG16 and VGG19, as feature extractors whereas the output features were used to train a multiclass support vector machine (SVM) classifier. To evaluate our approach, we used RadEch database of 8 ground moving targets classes. Our approach outperformed the state of the art methods, using the same database, with an accuracy of 96.56%.

Original languageBritish English
Title of host publication2018 19th International Radar Symposium, IRS 2018
EditorsHermann Rohling
PublisherIEEE Computer Society
ISBN (Print)9783736995451
DOIs
StatePublished - 27 Aug 2018
Event19th International Radar Symposium, IRS 2018 - Bonn, Germany
Duration: 20 Jun 201822 Jun 2018

Publication series

NameProceedings International Radar Symposium
Volume2018-June
ISSN (Print)2155-5753

Conference

Conference19th International Radar Symposium, IRS 2018
Country/TerritoryGermany
CityBonn
Period20/06/1822/06/18

Fingerprint

Dive into the research topics of 'Ground moving radar targets classification based on spectrogram images using convolutional neural networks'. Together they form a unique fingerprint.

Cite this