Simulation-based Approach to Classification of Airborne Drones

Lasse Lehmann; Jørgen Dall

doi:10.1109/RadarConf2043947.2020.9266405

Simulation-based Approach to Classification of Airborne Drones

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Recognition of drone type provides valuable information to assess the capability of drones, which is essential to airspace monitoring. Classification of drones on the basis of radar data is dominated by the use of supervised learning, which exploits different and often combined representations of the micro-Doppler signatures of the target. However, it is expensive and cumbersome building a catalogue of several drone micro-Doppler signatures using real data. We introduce a simulation-frame-work to generate radar data from point-scatterer targets, with associated radar cross section evaluated using physical optics. Small scale lab tests validate the fidelity of the simulated radar data, while the utility of the synthetic data for classification is tested using established methodology for classification.

Original language	English
Title of host publication	Proceedings of the 2020 IEEE Radar Conference (RadarConf20)
Number of pages	6
Publisher	IEEE
Publication date	2020
ISBN (Electronic)	978-1-7281-8942-0
DOIs	https://doi.org/10.1109/RadarConf2043947.2020.9266405
Publication status	Published - 2020
Event	IEEE Radar Conference 2020 - Virtual event, Florence, Italy Duration: 21 Sep 2020 → 25 Sep 2020 https://www.radarconf20.org/

Conference

Conference	IEEE Radar Conference 2020
Location	Virtual event
Country/Territory	Italy
City	Florence
Period	21/09/2020 → 25/09/2020
Internet address	https://www.radarconf20.org/

Series	Ieee National Radar Conference - Proceedings
ISSN	1097-5659

Keywords

Micro-Doppler
Drone classification
Radar cross section modelling
Radar simulation
Machine learning

Access to Document

10.1109/RadarConf2043947.2020.9266405

SFX availability

Full text

Cite this

@inproceedings{0f0a1cd696df461b8930ba2b190acf14,

title = "Simulation-based Approach to Classification of Airborne Drones",

abstract = "Recognition of drone type provides valuable information to assess the capability of drones, which is essential to airspace monitoring. Classification of drones on the basis of radar data is dominated by the use of supervised learning, which exploits different and often combined representations of the micro-Doppler signatures of the target. However, it is expensive and cumbersome building a catalogue of several drone micro-Doppler signatures using real data. We introduce a simulation-frame-work to generate radar data from point-scatterer targets, with associated radar cross section evaluated using physical optics. Small scale lab tests validate the fidelity of the simulated radar data, while the utility of the synthetic data for classification is tested using established methodology for classification.",

keywords = "Micro-Doppler, Drone classification, Radar cross section modelling, Radar simulation, Machine learning",

author = "Lasse Lehmann and J{\o}rgen Dall",

year = "2020",

doi = "10.1109/RadarConf2043947.2020.9266405",

language = "English",

series = "Ieee National Radar Conference - Proceedings",

publisher = "IEEE",

booktitle = "Proceedings of the 2020 IEEE Radar Conference (RadarConf20)",

address = "United States",

note = "IEEE Radar Conference 2020, IEEE RadarConf20 ; Conference date: 21-09-2020 Through 25-09-2020",

url = "https://www.radarconf20.org/",

}

TY - GEN

T1 - Simulation-based Approach to Classification of Airborne Drones

AU - Lehmann, Lasse

AU - Dall, Jørgen

PY - 2020

Y1 - 2020

N2 - Recognition of drone type provides valuable information to assess the capability of drones, which is essential to airspace monitoring. Classification of drones on the basis of radar data is dominated by the use of supervised learning, which exploits different and often combined representations of the micro-Doppler signatures of the target. However, it is expensive and cumbersome building a catalogue of several drone micro-Doppler signatures using real data. We introduce a simulation-frame-work to generate radar data from point-scatterer targets, with associated radar cross section evaluated using physical optics. Small scale lab tests validate the fidelity of the simulated radar data, while the utility of the synthetic data for classification is tested using established methodology for classification.

AB - Recognition of drone type provides valuable information to assess the capability of drones, which is essential to airspace monitoring. Classification of drones on the basis of radar data is dominated by the use of supervised learning, which exploits different and often combined representations of the micro-Doppler signatures of the target. However, it is expensive and cumbersome building a catalogue of several drone micro-Doppler signatures using real data. We introduce a simulation-frame-work to generate radar data from point-scatterer targets, with associated radar cross section evaluated using physical optics. Small scale lab tests validate the fidelity of the simulated radar data, while the utility of the synthetic data for classification is tested using established methodology for classification.

KW - Micro-Doppler

KW - Drone classification

KW - Radar cross section modelling

KW - Radar simulation

KW - Machine learning

U2 - 10.1109/RadarConf2043947.2020.9266405

DO - 10.1109/RadarConf2043947.2020.9266405

M3 - Article in proceedings

T3 - Ieee National Radar Conference - Proceedings

BT - Proceedings of the 2020 IEEE Radar Conference (RadarConf20)

PB - IEEE

T2 - IEEE Radar Conference 2020

Y2 - 21 September 2020 through 25 September 2020

ER -

Simulation-based Approach to Classification of Airborne Drones

Abstract

Conference

Keywords

Access to Document

SFX availability

Fingerprint

Cite this