Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Jul 21;21(15):4953.
doi: 10.3390/s21154953.

Audio-Based Drone Detection and Identification Using Deep Learning Techniques with Dataset Enhancement through Generative Adversarial Networks

Sara Al-Emadi  1 , Abdulla Al-Ali  1 , Abdulaziz Al-Ali  2
Affiliations

Audio-Based Drone Detection and Identification Using Deep Learning Techniques with Dataset Enhancement through Generative Adversarial Networks

Sara Al-Emadi et al. Sensors (Basel). .

Abstract

Drones are becoming increasingly popular not only for recreational purposes but in day-to-day applications in engineering, medicine, logistics, security and others. In addition to their useful applications, an alarming concern in regard to the physical infrastructure security, safety and privacy has arisen due to the potential of their use in malicious activities. To address this problem, we propose a novel solution that automates the drone detection and identification processes using a drone's acoustic features with different deep learning algorithms. However, the lack of acoustic drone datasets hinders the ability to implement an effective solution. In this paper, we aim to fill this gap by introducing a hybrid drone acoustic dataset composed of recorded drone audio clips and artificially generated drone audio samples using a state-of-the-art deep learning technique known as the Generative Adversarial Network. Furthermore, we examine the effectiveness of using drone audio with different deep learning algorithms, namely, the Convolutional Neural Network, the Recurrent Neural Network and the Convolutional Recurrent Neural Network in drone detection and identification. Moreover, we investigate the impact of our proposed hybrid dataset in drone detection. Our findings prove the advantage of using deep learning techniques for drone detection and identification while confirming our hypothesis on the benefits of using the Generative Adversarial Networks to generate real-like drone audio clips with an aim of enhancing the detection of new and unfamiliar drones.

Keywords: Convolutional Neural Network CNN; Convolutional Recurrent Neural Network CRNN; Generative Adversarial Networks GAN; Recurrent Neural Network RNN; UAV; acoustic fingerprinting; artificial intelligence; deep learning; drone; drone audio dataset; drone detection; drone identification; machine learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Proposed Anti-drone system.
Figure 2
Figure 2
High level design of the proposed framework.
Figure 3
Figure 3
Example of drone noise in spectrogram representation © [2019] IEEE. Reprinted, with permission, from [38].
Figure 4
Figure 4
Example of other noise in spectrogram representation © [2019] IEEE. Reprinted, with permission, from [38].
Figure 5
Figure 5
Example of the training and validation phases of CRNN for binary classification in a single run.
Figure 6
Figure 6
Example of the training and validation phases of CRNN for multi-class classification in a single run.
Figure 7
Figure 7
CPU time Results [38].
Figure 8
Figure 8
The performance, in terms of recall, of the average CNN models trained on the R4 drone dataset and tested on known (recorded) drone types (which the model has seen during the training phase). Whereas, the yellow bars are when tested on new and unknown types of drones.
Figure 9
Figure 9
Breakdown of Experiment 2.
Figure 10
Figure 10
The performance of the average CNN models trained on R4 Vs. RG drone dataset and tested on seen drones of in terms of recall.
Figure 11
Figure 11
The performance of the average CNN models trained on the R4 vs. RG drone dataset and tested on unseen drones of in terms of recall.
Figure 12
Figure 12
The performance of the average CNN models trained on all proposed drone datasets and tested on unseen drones of in terms of recall.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Berni J.A.J., Zarco-Tejada P.J., Suarez L., Fereres E. Thermal and Narrowband Multispectral Remote Sensing for Vegetation Monitoring from an Unmanned Aerial Vehicle. IEEE Trans. Geosci. Remote Sens. 2009;47:722–738. doi: 10.1109/TGRS.2008.2010457. - DOI
    1. Ciullo V., Rossi L., Toulouse T., Pieri A. Fire Geometrical Characteristics Estimation Using a Visible Stereovision System Carried by Unmanned Aerial Vehicle; Proceedings of the 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV); Singapore. 18–21 November 2018; pp. 1216–1221. - DOI
    1. Katsigiannis P., Misopolinos L., Liakopoulos V., Alexandridis T.K., Zalidis G. An autonomous multi-sensor UAV system for reduced-input precision agriculture applications; Proceedings of the 2016 24th Mediterranean Conference on Control and Automation (MED); Athens, Greece. 21–24 June 2016; pp. 60–64. - DOI
    1. Tariq R., Rahim M., Aslam N., Bawany N., Faseeha U. DronAID: A Smart Human Detection Drone for Rescue; Proceedings of the 2018 15th International Conference on Smart Cities: Improving Quality of Life Using ICT IoT (HONET-ICT); Islamabad, Pakistan. 8–10 October 2018; pp. 33–37. - DOI
    1. ’Sustained’ Drone Attack Closed Gatwick, Airport Says. BBC News, 20 February 2019. [(accessed on 27 June 2019)]; Available online: https://www.bbc.com/news/business-47302902.

LinkOut - more resources