Multi-time frequency analysis and classification of a micro-drone carrying payloads using multistatic radar
This article presents an analysis of three multi-domain transformations applied to radar data of a micro-drone operating in an open field, with a payload (between 200 and 600 g) and without a payload. Inferring the presence of a drone attempting to transport a payload beyond its normal operating con...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2019-08-01
|
Series: | The Journal of Engineering |
Subjects: | |
Online Access: | https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0551 |
id |
doaj-326fc3f68a3543bf87f2454e73628082 |
---|---|
record_format |
Article |
spelling |
doaj-326fc3f68a3543bf87f2454e736280822021-04-02T13:17:45ZengWileyThe Journal of Engineering2051-33052019-08-0110.1049/joe.2019.0551JOE.2019.0551Multi-time frequency analysis and classification of a micro-drone carrying payloads using multistatic radarJarez S. Patel0Caesar Al-Ameri1Francesco Fioranelli2David Anderson3School of Engineering, University of Glasgow, University AvenueSchool of Engineering, University of Glasgow, University AvenueSchool of Engineering, University of Glasgow, University AvenueSchool of Engineering, University of Glasgow, University AvenueThis article presents an analysis of three multi-domain transformations applied to radar data of a micro-drone operating in an open field, with a payload (between 200 and 600 g) and without a payload. Inferring the presence of a drone attempting to transport a payload beyond its normal operating conditions is a key enabler in prospective low altitude airspace security systems. Two scenarios of operation were explored, the first with the drone hovering and the second with the drone flying. Both were accomplished through real experimental trials, undertaken with the multistatic radar, NetRAD. The images generated as a result of the domain transformations were fed into a pretrained convolutional neural network (CNN), known as AlexNet and were treated as a six-class classification problem. Very promising accuracies were obtained, with on average 95.1% for the case of the drone hovering and 96.6% for the case of the drone flying. The activations that these variety of images triggered within the CNN were then visualised to better understand the specific features that the network was learning and distinguishing between, in order to successfully achieve classification.https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0551learning (artificial intelligence)image classificationautonomous aerial vehiclestime-frequency analysisconvolutional neural netsradar applicationsalexnetnetradcnnmicrodronepretrained convolutional neural networkdomain transformationsprospective low altitude airspace security systemsnormal operating conditionsopen fieldradar datamultidomain transformationsmultistatic radarmultitime frequency analysisdrone hoveringsix-class classification problem |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jarez S. Patel Caesar Al-Ameri Francesco Fioranelli David Anderson |
spellingShingle |
Jarez S. Patel Caesar Al-Ameri Francesco Fioranelli David Anderson Multi-time frequency analysis and classification of a micro-drone carrying payloads using multistatic radar The Journal of Engineering learning (artificial intelligence) image classification autonomous aerial vehicles time-frequency analysis convolutional neural nets radar applications alexnet netrad cnn microdrone pretrained convolutional neural network domain transformations prospective low altitude airspace security systems normal operating conditions open field radar data multidomain transformations multistatic radar multitime frequency analysis drone hovering six-class classification problem |
author_facet |
Jarez S. Patel Caesar Al-Ameri Francesco Fioranelli David Anderson |
author_sort |
Jarez S. Patel |
title |
Multi-time frequency analysis and classification of a micro-drone carrying payloads using multistatic radar |
title_short |
Multi-time frequency analysis and classification of a micro-drone carrying payloads using multistatic radar |
title_full |
Multi-time frequency analysis and classification of a micro-drone carrying payloads using multistatic radar |
title_fullStr |
Multi-time frequency analysis and classification of a micro-drone carrying payloads using multistatic radar |
title_full_unstemmed |
Multi-time frequency analysis and classification of a micro-drone carrying payloads using multistatic radar |
title_sort |
multi-time frequency analysis and classification of a micro-drone carrying payloads using multistatic radar |
publisher |
Wiley |
series |
The Journal of Engineering |
issn |
2051-3305 |
publishDate |
2019-08-01 |
description |
This article presents an analysis of three multi-domain transformations applied to radar data of a micro-drone operating in an open field, with a payload (between 200 and 600 g) and without a payload. Inferring the presence of a drone attempting to transport a payload beyond its normal operating conditions is a key enabler in prospective low altitude airspace security systems. Two scenarios of operation were explored, the first with the drone hovering and the second with the drone flying. Both were accomplished through real experimental trials, undertaken with the multistatic radar, NetRAD. The images generated as a result of the domain transformations were fed into a pretrained convolutional neural network (CNN), known as AlexNet and were treated as a six-class classification problem. Very promising accuracies were obtained, with on average 95.1% for the case of the drone hovering and 96.6% for the case of the drone flying. The activations that these variety of images triggered within the CNN were then visualised to better understand the specific features that the network was learning and distinguishing between, in order to successfully achieve classification. |
topic |
learning (artificial intelligence) image classification autonomous aerial vehicles time-frequency analysis convolutional neural nets radar applications alexnet netrad cnn microdrone pretrained convolutional neural network domain transformations prospective low altitude airspace security systems normal operating conditions open field radar data multidomain transformations multistatic radar multitime frequency analysis drone hovering six-class classification problem |
url |
https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0551 |
work_keys_str_mv |
AT jarezspatel multitimefrequencyanalysisandclassificationofamicrodronecarryingpayloadsusingmultistaticradar AT caesaralameri multitimefrequencyanalysisandclassificationofamicrodronecarryingpayloadsusingmultistaticradar AT francescofioranelli multitimefrequencyanalysisandclassificationofamicrodronecarryingpayloadsusingmultistaticradar AT davidanderson multitimefrequencyanalysisandclassificationofamicrodronecarryingpayloadsusingmultistaticradar |
_version_ |
1721565561196904448 |