Bird and micro-drone spectral width and classification

Daniel White; Mohammed Jahangir; Joseph P.  Wayman; Jim Reynolds; Jon Sadler; Michail Antoniou

doi:10.23919/IRS57608.2023.10172408

Bird and micro-drone spectral width and classification

Daniel White^*, Mohammed Jahangir, Joseph P. Wayman, Jim Reynolds, Jon Sadler, Michail Antoniou

^*Corresponding author for this work

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

155 Downloads (Pure)

Abstract

This paper reports on the class separability of spectrograms featuring bird and micro-drone targets produced by an L-Band staring radar. Multi-rotor drones with small propellor blades are less likely to show strong micro-Doppler sidebands depending on the range and operating frequency. With this, we were incentivized to measure the separability of the target classes relying only on the body Doppler information captured in the spectrograms. A spectral width feature extraction method was tested using both a set of single drone and bird targets, as well as a larger dataset including spectrograms containing multiple targets and a mixture of classes. These features were employed to inform a simple classifier yielding an 83% classification accuracy in the single target case. The results were then compared to a convolutional neural network baseline that achieved 89% accuracy on the larger, more complex dataset.

Original language	English
Title of host publication	2023 24th International Radar Symposium (IRS)
Publisher	IEEE
ISBN (Electronic)	9783944976341, 9783944976358 (USB)
ISBN (Print)	9781665456821 (PoD)
DOIs	https://doi.org/10.23919/IRS57608.2023.10172408
Publication status	E-pub ahead of print - 11 Jul 2023
Event	International Radar Symposium IRS 2023 - Berlin, Germany Duration: 24 May 2023 → 26 Jul 2023

Publication series

Name	Proceedings International Radar Symposium
Publisher	IEEE
ISSN (Print)	2155-5745
ISSN (Electronic)	2155-5753

Conference

Conference	International Radar Symposium IRS 2023
Abbreviated title	IRS 2023
Country/Territory	Germany
City	Berlin
Period	24/05/23 → 26/07/23

Keywords

Target tracking
Propulsion
Birds
Radar tracking
Trajectory
Doppler effect
Convolutional neural networks

Access to Document

10.23919/IRS57608.2023.10172408Licence: None: All rights reserved

ReynoldsS2023Bird
D. White, M. Jahangir, J. P. Wayman, S. J. Reynolds, J. P. Sadler and M. Antoniou, "Bird and Micro-Drone Doppler Spectral Width and Classification," 2023 24th International Radar Symposium (IRS), Berlin, Germany, 2023, pp. 1-10, doi: 10.23919/IRS57608.2023.10172408. © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 1.18 MBLicence: Other (please specify with Rights Statement)

MEFA: Mapping and Enabling Future Airspace
Reynolds, J. (Co-Investigator), Antoniou, M. (Principal Investigator), Sadler, J. (Co-Investigator), Baker, C. (Co-Investigator) & Baker, C. (Co-Investigator)
Engineering & Physical Science Research Council
1/04/20 → 31/03/24
Project: Research Councils
UK National Quantum Technology Hub in Sensing and Timing
Attallah, M. (Co-Investigator), Jones, R. (Co-Investigator), Metje, N. (Co-Investigator), Constantinou, C. (Co-Investigator), Faramarzi, A. (Co-Investigator), Singh, Y. (Co-Investigator), Holynski, M. (Principal Investigator), Bongs, K. (Co-Investigator), Baker, C. (Co-Investigator), Antoniou, M. (Co-Investigator) & Stewart, E. (Co-Investigator)
Engineering & Physical Science Research Council
1/12/19 → 30/11/24
Project: Research Councils

Cite this

@inproceedings{b967e759103c4a9eab7f266f54e7965a,

title = "Bird and micro-drone spectral width and classification",

abstract = "This paper reports on the class separability of spectrograms featuring bird and micro-drone targets produced by an L-Band staring radar. Multi-rotor drones with small propellor blades are less likely to show strong micro-Doppler sidebands depending on the range and operating frequency. With this, we were incentivized to measure the separability of the target classes relying only on the body Doppler information captured in the spectrograms. A spectral width feature extraction method was tested using both a set of single drone and bird targets, as well as a larger dataset including spectrograms containing multiple targets and a mixture of classes. These features were employed to inform a simple classifier yielding an 83% classification accuracy in the single target case. The results were then compared to a convolutional neural network baseline that achieved 89% accuracy on the larger, more complex dataset.",

keywords = "Target tracking, Propulsion, Birds, Radar tracking, Trajectory, Doppler effect, Convolutional neural networks",

author = "Daniel White and Mohammed Jahangir and Wayman, {Joseph P.} and Jim Reynolds and Jon Sadler and Michail Antoniou",

year = "2023",

month = jul,

day = "11",

doi = "10.23919/IRS57608.2023.10172408",

language = "English",

isbn = "9781665456821 (PoD)",

series = "Proceedings International Radar Symposium",

publisher = "IEEE",

booktitle = "2023 24th International Radar Symposium (IRS)",

note = "International Radar Symposium IRS 2023, IRS 2023 ; Conference date: 24-05-2023 Through 26-07-2023",

}

TY - GEN

T1 - Bird and micro-drone spectral width and classification

AU - White, Daniel

AU - Jahangir, Mohammed

AU - Wayman, Joseph P.

AU - Reynolds, Jim

AU - Sadler, Jon

AU - Antoniou, Michail

PY - 2023/7/11

Y1 - 2023/7/11

N2 - This paper reports on the class separability of spectrograms featuring bird and micro-drone targets produced by an L-Band staring radar. Multi-rotor drones with small propellor blades are less likely to show strong micro-Doppler sidebands depending on the range and operating frequency. With this, we were incentivized to measure the separability of the target classes relying only on the body Doppler information captured in the spectrograms. A spectral width feature extraction method was tested using both a set of single drone and bird targets, as well as a larger dataset including spectrograms containing multiple targets and a mixture of classes. These features were employed to inform a simple classifier yielding an 83% classification accuracy in the single target case. The results were then compared to a convolutional neural network baseline that achieved 89% accuracy on the larger, more complex dataset.

AB - This paper reports on the class separability of spectrograms featuring bird and micro-drone targets produced by an L-Band staring radar. Multi-rotor drones with small propellor blades are less likely to show strong micro-Doppler sidebands depending on the range and operating frequency. With this, we were incentivized to measure the separability of the target classes relying only on the body Doppler information captured in the spectrograms. A spectral width feature extraction method was tested using both a set of single drone and bird targets, as well as a larger dataset including spectrograms containing multiple targets and a mixture of classes. These features were employed to inform a simple classifier yielding an 83% classification accuracy in the single target case. The results were then compared to a convolutional neural network baseline that achieved 89% accuracy on the larger, more complex dataset.

KW - Target tracking

KW - Propulsion

KW - Birds

KW - Radar tracking

KW - Trajectory

KW - Doppler effect

KW - Convolutional neural networks

U2 - 10.23919/IRS57608.2023.10172408

DO - 10.23919/IRS57608.2023.10172408

M3 - Conference contribution

SN - 9781665456821 (PoD)

T3 - Proceedings International Radar Symposium

BT - 2023 24th International Radar Symposium (IRS)

PB - IEEE

T2 - International Radar Symposium IRS 2023

Y2 - 24 May 2023 through 26 July 2023

ER -

Bird and micro-drone spectral width and classification

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Projects

MEFA: Mapping and Enabling Future Airspace

UK National Quantum Technology Hub in Sensing and Timing

Cite this