An initial investigation into using convolutional neural networks for classification of drones

Holly Dale; Chris Baker; Michail Antoniou; Mohammed Jahangir

doi:10.1109/RADAR42522.2020.9114745

An initial investigation into using convolutional neural networks for classification of drones

Holly Dale, Chris Baker, Michail Antoniou, Mohammed Jahangir

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

The use of convolutional neural networks (CNNs) in drone and non-drone classification is investigated in this paper. A classifier is trained on radar spectrograms obtained using an L-band staring radar and the performance is assessed and compared with a machine learning benchmark. Initial results have shown the CNN to achieve a correct classification performance of up to 98.89%.

Original language	English
Title of host publication	2020 IEEE International Radar Conference, RADAR 2020
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	618-623
Number of pages	6
ISBN (Electronic)	9781728168128
DOIs	https://doi.org/10.1109/RADAR42522.2020.9114745
Publication status	Published - Apr 2020
Event	2020 IEEE International Radar Conference, RADAR 2020 - Washington, United States Duration: 28 Apr 2020 → 30 Apr 2020

Publication series

Name	2020 IEEE International Radar Conference, RADAR 2020

Conference

Conference	2020 IEEE International Radar Conference, RADAR 2020
Country/Territory	United States
City	Washington
Period	28/04/20 → 30/04/20

Keywords

Birds
Classification
Deep learning
Machine learning
Signal processing
Staring radar
UAVs

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing
Instrumentation

Access to Document

10.1109/RADAR42522.2020.9114745

Cite this

Dale, H., Baker, C., Antoniou, M., & Jahangir, M. (2020). An initial investigation into using convolutional neural networks for classification of drones. In 2020 IEEE International Radar Conference, RADAR 2020 (pp. 618-623). Article 09114745 (2020 IEEE International Radar Conference, RADAR 2020). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/RADAR42522.2020.9114745

@inproceedings{31c2a5cdbab84fa1bef62bff5ea8b2fb,

title = "An initial investigation into using convolutional neural networks for classification of drones",

abstract = "The use of convolutional neural networks (CNNs) in drone and non-drone classification is investigated in this paper. A classifier is trained on radar spectrograms obtained using an L-band staring radar and the performance is assessed and compared with a machine learning benchmark. Initial results have shown the CNN to achieve a correct classification performance of up to 98.89%.",

keywords = "Birds, Classification, Deep learning, Machine learning, Signal processing, Staring radar, UAVs",

author = "Holly Dale and Chris Baker and Michail Antoniou and Mohammed Jahangir",

year = "2020",

month = apr,

doi = "10.1109/RADAR42522.2020.9114745",

language = "English",

series = "2020 IEEE International Radar Conference, RADAR 2020",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "618--623",

booktitle = "2020 IEEE International Radar Conference, RADAR 2020",

note = "2020 IEEE International Radar Conference, RADAR 2020 ; Conference date: 28-04-2020 Through 30-04-2020",

}

Dale, H, Baker, C, Antoniou, M & Jahangir, M 2020, An initial investigation into using convolutional neural networks for classification of drones. in 2020 IEEE International Radar Conference, RADAR 2020., 09114745, 2020 IEEE International Radar Conference, RADAR 2020, Institute of Electrical and Electronics Engineers (IEEE), pp. 618-623, 2020 IEEE International Radar Conference, RADAR 2020, Washington, United States, 28/04/20. https://doi.org/10.1109/RADAR42522.2020.9114745

An initial investigation into using convolutional neural networks for classification of drones. / Dale, Holly; Baker, Chris; Antoniou, Michail et al.
2020 IEEE International Radar Conference, RADAR 2020. Institute of Electrical and Electronics Engineers (IEEE), 2020. p. 618-623 09114745 (2020 IEEE International Radar Conference, RADAR 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - An initial investigation into using convolutional neural networks for classification of drones

AU - Dale, Holly

AU - Baker, Chris

AU - Antoniou, Michail

AU - Jahangir, Mohammed

PY - 2020/4

Y1 - 2020/4

N2 - The use of convolutional neural networks (CNNs) in drone and non-drone classification is investigated in this paper. A classifier is trained on radar spectrograms obtained using an L-band staring radar and the performance is assessed and compared with a machine learning benchmark. Initial results have shown the CNN to achieve a correct classification performance of up to 98.89%.

AB - The use of convolutional neural networks (CNNs) in drone and non-drone classification is investigated in this paper. A classifier is trained on radar spectrograms obtained using an L-band staring radar and the performance is assessed and compared with a machine learning benchmark. Initial results have shown the CNN to achieve a correct classification performance of up to 98.89%.

KW - Birds

KW - Classification

KW - Deep learning

KW - Machine learning

KW - Signal processing

KW - Staring radar

KW - UAVs

UR - http://www.scopus.com/inward/record.url?scp=85090336275&partnerID=8YFLogxK

U2 - 10.1109/RADAR42522.2020.9114745

DO - 10.1109/RADAR42522.2020.9114745

M3 - Conference contribution

AN - SCOPUS:85090336275

T3 - 2020 IEEE International Radar Conference, RADAR 2020

SP - 618

EP - 623

BT - 2020 IEEE International Radar Conference, RADAR 2020

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2020 IEEE International Radar Conference, RADAR 2020

Y2 - 28 April 2020 through 30 April 2020

ER -

Dale H, Baker C, Antoniou M , Jahangir M. An initial investigation into using convolutional neural networks for classification of drones. In 2020 IEEE International Radar Conference, RADAR 2020. Institute of Electrical and Electronics Engineers (IEEE). 2020. p. 618-623. 09114745. (2020 IEEE International Radar Conference, RADAR 2020). doi: 10.1109/RADAR42522.2020.9114745

An initial investigation into using convolutional neural networks for classification of drones

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this