Classification of human motions using empirical mode decomposition of human micro-doppler signatures

Dustin P. Fairchild, Ram Mohan Narayanan

Research output: Contribution to journalArticle

83 Citations (Scopus)

Abstract

The ability to identify human movements can serve as an important tool in many different applications such as surveillance, military combat situations, search and rescue operations and patient monitoring in hospitals. This information can provide soldiers, security personnel and search and rescue workers with critical knowledge that can be used to potentially save lives and/or avoid dangerous situations. Most research involving human activity recognition employs the short-time Fourier transform (STFT) as a method of analysing human micro-Doppler signatures. However, the STFT has time-frequency resolution limitations and Fourier transform-based methods are not well-suited for use with non-stationary and non-linear signals. The authors approach uses the empirical mode decomposition to produce a unique feature vector from the human micro-Doppler signals following which a support vector machine is used to classify human motions. This study presents simulations of simple human motions, which are subsequently validated using experimental data obtained from both an S-band radar and a W-band millimetre wave (mm-wave) radar. Very good classification accuracies are obtained at distances of up to 90 m between the human and the radar.

Original languageEnglish (US)
Pages (from-to)425-434
Number of pages10
JournalIET Radar, Sonar and Navigation
Volume8
Issue number5
DOIs
StatePublished - 2014

Fingerprint

Fourier transforms
Radar
Decomposition
Patient monitoring
Millimeter waves
Support vector machines
Personnel

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

@article{c5a8a98281394c71bccc6ac502c92553,
title = "Classification of human motions using empirical mode decomposition of human micro-doppler signatures",
abstract = "The ability to identify human movements can serve as an important tool in many different applications such as surveillance, military combat situations, search and rescue operations and patient monitoring in hospitals. This information can provide soldiers, security personnel and search and rescue workers with critical knowledge that can be used to potentially save lives and/or avoid dangerous situations. Most research involving human activity recognition employs the short-time Fourier transform (STFT) as a method of analysing human micro-Doppler signatures. However, the STFT has time-frequency resolution limitations and Fourier transform-based methods are not well-suited for use with non-stationary and non-linear signals. The authors approach uses the empirical mode decomposition to produce a unique feature vector from the human micro-Doppler signals following which a support vector machine is used to classify human motions. This study presents simulations of simple human motions, which are subsequently validated using experimental data obtained from both an S-band radar and a W-band millimetre wave (mm-wave) radar. Very good classification accuracies are obtained at distances of up to 90 m between the human and the radar.",
author = "Fairchild, {Dustin P.} and Narayanan, {Ram Mohan}",
year = "2014",
doi = "10.1049/iet-rsn.2013.0165",
language = "English (US)",
volume = "8",
pages = "425--434",
journal = "IET Radar, Sonar and Navigation",
issn = "1751-8784",
publisher = "Institution of Engineering and Technology",
number = "5",

}

Classification of human motions using empirical mode decomposition of human micro-doppler signatures. / Fairchild, Dustin P.; Narayanan, Ram Mohan.

In: IET Radar, Sonar and Navigation, Vol. 8, No. 5, 2014, p. 425-434.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Classification of human motions using empirical mode decomposition of human micro-doppler signatures

AU - Fairchild, Dustin P.

AU - Narayanan, Ram Mohan

PY - 2014

Y1 - 2014

N2 - The ability to identify human movements can serve as an important tool in many different applications such as surveillance, military combat situations, search and rescue operations and patient monitoring in hospitals. This information can provide soldiers, security personnel and search and rescue workers with critical knowledge that can be used to potentially save lives and/or avoid dangerous situations. Most research involving human activity recognition employs the short-time Fourier transform (STFT) as a method of analysing human micro-Doppler signatures. However, the STFT has time-frequency resolution limitations and Fourier transform-based methods are not well-suited for use with non-stationary and non-linear signals. The authors approach uses the empirical mode decomposition to produce a unique feature vector from the human micro-Doppler signals following which a support vector machine is used to classify human motions. This study presents simulations of simple human motions, which are subsequently validated using experimental data obtained from both an S-band radar and a W-band millimetre wave (mm-wave) radar. Very good classification accuracies are obtained at distances of up to 90 m between the human and the radar.

AB - The ability to identify human movements can serve as an important tool in many different applications such as surveillance, military combat situations, search and rescue operations and patient monitoring in hospitals. This information can provide soldiers, security personnel and search and rescue workers with critical knowledge that can be used to potentially save lives and/or avoid dangerous situations. Most research involving human activity recognition employs the short-time Fourier transform (STFT) as a method of analysing human micro-Doppler signatures. However, the STFT has time-frequency resolution limitations and Fourier transform-based methods are not well-suited for use with non-stationary and non-linear signals. The authors approach uses the empirical mode decomposition to produce a unique feature vector from the human micro-Doppler signals following which a support vector machine is used to classify human motions. This study presents simulations of simple human motions, which are subsequently validated using experimental data obtained from both an S-band radar and a W-band millimetre wave (mm-wave) radar. Very good classification accuracies are obtained at distances of up to 90 m between the human and the radar.

UR - http://www.scopus.com/inward/record.url?scp=84901947786&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901947786&partnerID=8YFLogxK

U2 - 10.1049/iet-rsn.2013.0165

DO - 10.1049/iet-rsn.2013.0165

M3 - Article

VL - 8

SP - 425

EP - 434

JO - IET Radar, Sonar and Navigation

JF - IET Radar, Sonar and Navigation

SN - 1751-8784

IS - 5

ER -