FEASIBILITY OF DETECTING AND CLASSIFYING SMALL UNMANNED AERIAL SYSTEM THREATS USING ACOUSTIC DATA

Loading...
Thumbnail Image
Authors
Fleming, Austin G.
Subjects
UAV
UAS
sUAS
deep learning
machine learning
neural network
signal processing
drone
detection
AlexNet
Advisors
Yakimenko, Oleg A.
Durante Pereira Alves, Fabio D.
Date of Issue
2019-12
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
Unmanned aerial systems (UAS) have become a threat that the Department of Defense (DoD) must address. Malevolent actors have shown time and again that they will exploit any new technology for illicit ends. Current systems designed to defeat UAS threats have failed to demonstrate adequate performance. There is a capability gap in the DoD for countering the UAS threat. To address this, the author investigated the feasibility of detecting and classifying small UAS threats using acoustic data. The pre-trained convolutional neural network, AlexNet, was used as the method for detecting UAS. Acoustic data was collected in a variety of conditions and converted to a JPEG representation of the continuous wavelet transform. Then the data was used to train and evaluate the performance of AlexNet in detecting and classifying drones. This research will lay the foundation for addressing UAS detection using a combination of acoustic signatures and deep learning.
Type
Thesis
Description
Department
Systems Engineering (SE)
Organization
Identifiers
NPS Report Number
Sponsors
ONR
Funder
Format
Citation
Distribution Statement
Approved for public release; distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.
Collections