Micro-Doppler Mini-UAV Classification Using Empirical-Mode Decomposition Features

Beom Seok Oh, Xin Guo, Fangyuan Wan, Kar Ann Toh, Zhiping Lin

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

In this letter, we propose an empirical-mode decomposition (EMD)-based method for automatic multicategory mini-unmanned aerial vehicle (UAV) classification. The radar echo signal is first decomposed into a set of oscillating waveforms by EMD. Then, eight statistical and geometrical features are extracted from the oscillating waveforms to capture the phenomenon of blade flashes. After feature normalization and fusion, a nonlinear support vector machine is trained for target class-label prediction. Our empirical results on real measurement of radar signals show encouraging mini-UAV classification accuracy performance.

Original languageEnglish
Article number8239598
Pages (from-to)227-231
Number of pages5
JournalIEEE Geoscience and Remote Sensing Letters
Volume15
Issue number2
DOIs
Publication statusPublished - 2018 Feb 1

Fingerprint

Unmanned aerial vehicles (UAV)
Radar
radar
decomposition
Decomposition
Support vector machines
Labels
Fusion reactions
prediction
vehicle
support vector machine
normalisation
method

All Science Journal Classification (ASJC) codes

  • Geotechnical Engineering and Engineering Geology
  • Electrical and Electronic Engineering

Cite this

Oh, Beom Seok ; Guo, Xin ; Wan, Fangyuan ; Toh, Kar Ann ; Lin, Zhiping. / Micro-Doppler Mini-UAV Classification Using Empirical-Mode Decomposition Features. In: IEEE Geoscience and Remote Sensing Letters. 2018 ; Vol. 15, No. 2. pp. 227-231.
@article{c18541b60569455081123182a5d89bc6,
title = "Micro-Doppler Mini-UAV Classification Using Empirical-Mode Decomposition Features",
abstract = "In this letter, we propose an empirical-mode decomposition (EMD)-based method for automatic multicategory mini-unmanned aerial vehicle (UAV) classification. The radar echo signal is first decomposed into a set of oscillating waveforms by EMD. Then, eight statistical and geometrical features are extracted from the oscillating waveforms to capture the phenomenon of blade flashes. After feature normalization and fusion, a nonlinear support vector machine is trained for target class-label prediction. Our empirical results on real measurement of radar signals show encouraging mini-UAV classification accuracy performance.",
author = "Oh, {Beom Seok} and Xin Guo and Fangyuan Wan and Toh, {Kar Ann} and Zhiping Lin",
year = "2018",
month = "2",
day = "1",
doi = "10.1109/LGRS.2017.2781711",
language = "English",
volume = "15",
pages = "227--231",
journal = "IEEE Geoscience and Remote Sensing Letters",
issn = "1545-598X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

Micro-Doppler Mini-UAV Classification Using Empirical-Mode Decomposition Features. / Oh, Beom Seok; Guo, Xin; Wan, Fangyuan; Toh, Kar Ann; Lin, Zhiping.

In: IEEE Geoscience and Remote Sensing Letters, Vol. 15, No. 2, 8239598, 01.02.2018, p. 227-231.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Micro-Doppler Mini-UAV Classification Using Empirical-Mode Decomposition Features

AU - Oh, Beom Seok

AU - Guo, Xin

AU - Wan, Fangyuan

AU - Toh, Kar Ann

AU - Lin, Zhiping

PY - 2018/2/1

Y1 - 2018/2/1

N2 - In this letter, we propose an empirical-mode decomposition (EMD)-based method for automatic multicategory mini-unmanned aerial vehicle (UAV) classification. The radar echo signal is first decomposed into a set of oscillating waveforms by EMD. Then, eight statistical and geometrical features are extracted from the oscillating waveforms to capture the phenomenon of blade flashes. After feature normalization and fusion, a nonlinear support vector machine is trained for target class-label prediction. Our empirical results on real measurement of radar signals show encouraging mini-UAV classification accuracy performance.

AB - In this letter, we propose an empirical-mode decomposition (EMD)-based method for automatic multicategory mini-unmanned aerial vehicle (UAV) classification. The radar echo signal is first decomposed into a set of oscillating waveforms by EMD. Then, eight statistical and geometrical features are extracted from the oscillating waveforms to capture the phenomenon of blade flashes. After feature normalization and fusion, a nonlinear support vector machine is trained for target class-label prediction. Our empirical results on real measurement of radar signals show encouraging mini-UAV classification accuracy performance.

UR - http://www.scopus.com/inward/record.url?scp=85039765853&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85039765853&partnerID=8YFLogxK

U2 - 10.1109/LGRS.2017.2781711

DO - 10.1109/LGRS.2017.2781711

M3 - Article

VL - 15

SP - 227

EP - 231

JO - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

SN - 1545-598X

IS - 2

M1 - 8239598

ER -