Malicious UAV Detection Using Integrated Audio and Visual Features for Public Safety Applications

Malicious UAV Detection Using Integrated Audio and Visual Features for Public Safety Applications

Unmanned aerial vehicles (UAVs) have become popular in surveillance, security, and remote monitoring. However, they also pose serious security threats to public privacy. The timely detection of a malicious drone is currently an open research issue for security provisioning companies. Recently, the p...

Full description

Bibliographic Details
Main Authors: Sonain Jamil, Fawad, MuhibUr Rahman, Amin Ullah, Salman Badnava, Masoud Forsat, Seyed Sajad Mirjavadi
Format: Article
Language:English
Published: MDPI AG 2020-07-01
Series:Sensors
Subjects:
AlexNet
feature extraction
localization
public safety
malicious drones
surveillance
Online Access:https://www.mdpi.com/1424-8220/20/14/3923
id doaj-72b822797d7f4cc4b714341af12fae9c
record_format Article
spelling doaj-72b822797d7f4cc4b714341af12fae9c2020-11-25T03:07:30ZengMDPI AGSensors1424-82202020-07-01203923392310.3390/s20143923Malicious UAV Detection Using Integrated Audio and Visual Features for Public Safety ApplicationsSonain Jamil0Fawad1MuhibUr Rahman2Amin Ullah3Salman Badnava4Masoud Forsat5Seyed Sajad Mirjavadi6ACTSENA Research Group, Telecommunication Engineering Department, University of Engineering and Technology, Taxila, Punjab 47050, PakistanACTSENA Research Group, Telecommunication Engineering Department, University of Engineering and Technology, Taxila, Punjab 47050, PakistanDepartment of Electrical Engineering, Polytechnique Montreal, Montreal, QC H3T 1J4, CanadaCollege of Engineering & Computer Science (CECS), Center for Research in Computer Vision Lab (CRCV Lab), University of Central Florida (UCF), Orlando, FL 32816, USADepartment of Computer Science and Engineering, College of Engineering, Qatar University, P.O. Box Doha 2713, QatarDepartment of Mechanical and Industrial Engineering, College of Engineering, Qatar University, P.O. Box Doha 2713, QatarDepartment of Mechanical and Industrial Engineering, College of Engineering, Qatar University, P.O. Box Doha 2713, QatarUnmanned aerial vehicles (UAVs) have become popular in surveillance, security, and remote monitoring. However, they also pose serious security threats to public privacy. The timely detection of a malicious drone is currently an open research issue for security provisioning companies. Recently, the problem has been addressed by a plethora of schemes. However, each plan has a limitation, such as extreme weather conditions and huge dataset requirements. In this paper, we propose a novel framework consisting of the hybrid handcrafted and deep feature to detect and localize malicious drones from their sound and image information. The respective datasets include sounds and occluded images of birds, airplanes, and thunderstorms, with variations in resolution and illumination. Various kernels of the support vector machine (SVM) are applied to classify the features. Experimental results validate the improved performance of the proposed scheme compared to other related methods.https://www.mdpi.com/1424-8220/20/14/3923AlexNetfeature extractionlocalizationpublic safetymalicious dronessurveillance
collection DOAJ
language English
format Article
sources DOAJ
author Sonain Jamil
Fawad
MuhibUr Rahman
Amin Ullah
Salman Badnava
Masoud Forsat
Seyed Sajad Mirjavadi
spellingShingle Sonain Jamil
Fawad
MuhibUr Rahman
Amin Ullah
Salman Badnava
Masoud Forsat
Seyed Sajad Mirjavadi
Malicious UAV Detection Using Integrated Audio and Visual Features for Public Safety Applications
Sensors
AlexNet
feature extraction
localization
public safety
malicious drones
surveillance
author_facet Sonain Jamil
Fawad
MuhibUr Rahman
Amin Ullah
Salman Badnava
Masoud Forsat
Seyed Sajad Mirjavadi
author_sort Sonain Jamil
title Malicious UAV Detection Using Integrated Audio and Visual Features for Public Safety Applications
title_short Malicious UAV Detection Using Integrated Audio and Visual Features for Public Safety Applications
title_full Malicious UAV Detection Using Integrated Audio and Visual Features for Public Safety Applications
title_fullStr Malicious UAV Detection Using Integrated Audio and Visual Features for Public Safety Applications
title_full_unstemmed Malicious UAV Detection Using Integrated Audio and Visual Features for Public Safety Applications
title_sort malicious uav detection using integrated audio and visual features for public safety applications
publisher MDPI AG
series Sensors
issn 1424-8220
publishDate 2020-07-01
description Unmanned aerial vehicles (UAVs) have become popular in surveillance, security, and remote monitoring. However, they also pose serious security threats to public privacy. The timely detection of a malicious drone is currently an open research issue for security provisioning companies. Recently, the problem has been addressed by a plethora of schemes. However, each plan has a limitation, such as extreme weather conditions and huge dataset requirements. In this paper, we propose a novel framework consisting of the hybrid handcrafted and deep feature to detect and localize malicious drones from their sound and image information. The respective datasets include sounds and occluded images of birds, airplanes, and thunderstorms, with variations in resolution and illumination. Various kernels of the support vector machine (SVM) are applied to classify the features. Experimental results validate the improved performance of the proposed scheme compared to other related methods.
topic AlexNet
feature extraction
localization
public safety
malicious drones
surveillance
url https://www.mdpi.com/1424-8220/20/14/3923
work_keys_str_mv AT sonainjamil maliciousuavdetectionusingintegratedaudioandvisualfeaturesforpublicsafetyapplications
AT fawad maliciousuavdetectionusingintegratedaudioandvisualfeaturesforpublicsafetyapplications
AT muhiburrahman maliciousuavdetectionusingintegratedaudioandvisualfeaturesforpublicsafetyapplications
AT aminullah maliciousuavdetectionusingintegratedaudioandvisualfeaturesforpublicsafetyapplications
AT salmanbadnava maliciousuavdetectionusingintegratedaudioandvisualfeaturesforpublicsafetyapplications
AT masoudforsat maliciousuavdetectionusingintegratedaudioandvisualfeaturesforpublicsafetyapplications
AT seyedsajadmirjavadi maliciousuavdetectionusingintegratedaudioandvisualfeaturesforpublicsafetyapplications
_version_ 1724670077951803392

Similar Items