Next Article in Journal
Strength Analysis of Alternative Airframe Layouts of Regional Aircraft on the Basis of Automated Parametrical Models
Next Article in Special Issue
Online Identification-Verification-Prediction Method for Parallel System Control of UAVs
Previous Article in Journal
Aspect Ratio Driven Relationship between Nozzle Internal Flow and Supersonic Jet Mixing
Previous Article in Special Issue
Human–Machine Interface Design for Monitoring Safety Risks Associated with Operating Small Unmanned Aircraft Systems in Urban Areas
 
 
Article

Unmanned Aerial Vehicle Operating Mode Classification Using Deep Residual Learning Feature Extraction

1
Computer Science and Electronic Engineering Department, University of Essex, Colchester CO4 3SQ, UK
2
Air and Space Warfare Centre, Royal Air Force Waddington, Lincoln LN5 9NB, UK
*
Author to whom correspondence should be addressed.
Academic Editor: Enric Pastor
Aerospace 2021, 8(3), 79; https://doi.org/10.3390/aerospace8030079
Received: 23 February 2021 / Revised: 10 March 2021 / Accepted: 10 March 2021 / Published: 16 March 2021
(This article belongs to the Collection Unmanned Aerial Systems)
Unmanned Aerial Vehicles (UAVs) undoubtedly pose many security challenges. We need only look to the December 2018 Gatwick Airport incident for an example of the disruption UAVs can cause. In total, 1000 flights were grounded for 36 h over the Christmas period which was estimated to cost over 50 million pounds. In this paper, we introduce a novel approach which considers UAV detection as an imagery classification problem. We consider signal representations Power Spectral Density (PSD); Spectrogram, Histogram and raw IQ constellation as graphical images presented to a deep Convolution Neural Network (CNN) ResNet50 for feature extraction. Pre-trained on ImageNet, transfer learning is utilised to mitigate the requirement for a large signal dataset. We evaluate performance through machine learning classifier Logistic Regression. Three popular UAVs are classified in different modes; switched on; hovering; flying; flying with video; and no UAV present, creating a total of 10 classes. Our results, validated with 5-fold cross validation and an independent dataset, show PSD representation to produce over 91% accuracy for 10 classifications. Our paper treats UAV detection as an imagery classification problem by presenting signal representations as images to a ResNet50, utilising the benefits of transfer learning and outperforming previous work in the field. View Full-Text
Keywords: unmanned aerial vehicles; UAV detection; RF spectrum analysis; machine learning classification; deep learning; convolutional neural network; transfer learning; signal analysis unmanned aerial vehicles; UAV detection; RF spectrum analysis; machine learning classification; deep learning; convolutional neural network; transfer learning; signal analysis
Show Figures

Figure 1

MDPI and ACS Style

Swinney, C.J.; Woods, J.C. Unmanned Aerial Vehicle Operating Mode Classification Using Deep Residual Learning Feature Extraction. Aerospace 2021, 8, 79. https://doi.org/10.3390/aerospace8030079

AMA Style

Swinney CJ, Woods JC. Unmanned Aerial Vehicle Operating Mode Classification Using Deep Residual Learning Feature Extraction. Aerospace. 2021; 8(3):79. https://doi.org/10.3390/aerospace8030079

Chicago/Turabian Style

Swinney, Carolyn J., and John C. Woods. 2021. "Unmanned Aerial Vehicle Operating Mode Classification Using Deep Residual Learning Feature Extraction" Aerospace 8, no. 3: 79. https://doi.org/10.3390/aerospace8030079

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop