Radar micro-Doppler based human activity classification for indoor and outdoor environments

Matthew Zenaldin, Ram Mohan Narayanan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

This paper presents the results of our experimental investigation into how different environments impact the classification of human motion using radar micro-Doppler (MD) signatures. The environments studied include free space, through-thewall, leaf tree foliage, and needle tree foliage. Results on presented on classification of the following three motions: crawling, walking, and jogging. The classification task was designed how to best separate these movements. The human motion data were acquired using a monostatic coherent Doppler radar operating in the C-band at 6.5 GHz from a total of six human subjects. The received signals were analyzed in the time-frequency domain using the Short-time Fourier Transform (STFT) which was used for feature extraction. Classification was performed using a Support Vector Machine (SVM) using a Radial Basis Function (RBF). Classification accuracies in the range 80-90% were achieved to separate the three movements mentioned.

Original languageEnglish (US)
Title of host publicationRadar Sensor Technology XX
EditorsArmin Doerry, Kenneth I. Ranney
PublisherSPIE
Volume9829
ISBN (Electronic)9781510600706
DOIs
StatePublished - Jan 1 2016
EventRadar Sensor Technology XX - Baltimore, United States
Duration: Apr 18 2016Apr 21 2016

Other

OtherRadar Sensor Technology XX
CountryUnited States
CityBaltimore
Period4/18/164/21/16

Fingerprint

Doppler
Radar
radar
foliage
Motion
coherent radar
Short-time Fourier Transform
Doppler radar
walking
C band
Free Space
Experimental Investigation
Radial Functions
needles
pattern recognition
Needles
leaves
Feature Extraction
Support vector machines
Frequency Domain

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Zenaldin, M., & Narayanan, R. M. (2016). Radar micro-Doppler based human activity classification for indoor and outdoor environments. In A. Doerry, & K. I. Ranney (Eds.), Radar Sensor Technology XX (Vol. 9829). [98291B] SPIE. https://doi.org/10.1117/12.2228397
Zenaldin, Matthew ; Narayanan, Ram Mohan. / Radar micro-Doppler based human activity classification for indoor and outdoor environments. Radar Sensor Technology XX. editor / Armin Doerry ; Kenneth I. Ranney. Vol. 9829 SPIE, 2016.
@inproceedings{e5cdbd6233d2467f8cb833299b0bdeff,
title = "Radar micro-Doppler based human activity classification for indoor and outdoor environments",
abstract = "This paper presents the results of our experimental investigation into how different environments impact the classification of human motion using radar micro-Doppler (MD) signatures. The environments studied include free space, through-thewall, leaf tree foliage, and needle tree foliage. Results on presented on classification of the following three motions: crawling, walking, and jogging. The classification task was designed how to best separate these movements. The human motion data were acquired using a monostatic coherent Doppler radar operating in the C-band at 6.5 GHz from a total of six human subjects. The received signals were analyzed in the time-frequency domain using the Short-time Fourier Transform (STFT) which was used for feature extraction. Classification was performed using a Support Vector Machine (SVM) using a Radial Basis Function (RBF). Classification accuracies in the range 80-90{\%} were achieved to separate the three movements mentioned.",
author = "Matthew Zenaldin and Narayanan, {Ram Mohan}",
year = "2016",
month = "1",
day = "1",
doi = "10.1117/12.2228397",
language = "English (US)",
volume = "9829",
editor = "Armin Doerry and Ranney, {Kenneth I.}",
booktitle = "Radar Sensor Technology XX",
publisher = "SPIE",
address = "United States",

}

Zenaldin, M & Narayanan, RM 2016, Radar micro-Doppler based human activity classification for indoor and outdoor environments. in A Doerry & KI Ranney (eds), Radar Sensor Technology XX. vol. 9829, 98291B, SPIE, Radar Sensor Technology XX, Baltimore, United States, 4/18/16. https://doi.org/10.1117/12.2228397

Radar micro-Doppler based human activity classification for indoor and outdoor environments. / Zenaldin, Matthew; Narayanan, Ram Mohan.

Radar Sensor Technology XX. ed. / Armin Doerry; Kenneth I. Ranney. Vol. 9829 SPIE, 2016. 98291B.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Radar micro-Doppler based human activity classification for indoor and outdoor environments

AU - Zenaldin, Matthew

AU - Narayanan, Ram Mohan

PY - 2016/1/1

Y1 - 2016/1/1

N2 - This paper presents the results of our experimental investigation into how different environments impact the classification of human motion using radar micro-Doppler (MD) signatures. The environments studied include free space, through-thewall, leaf tree foliage, and needle tree foliage. Results on presented on classification of the following three motions: crawling, walking, and jogging. The classification task was designed how to best separate these movements. The human motion data were acquired using a monostatic coherent Doppler radar operating in the C-band at 6.5 GHz from a total of six human subjects. The received signals were analyzed in the time-frequency domain using the Short-time Fourier Transform (STFT) which was used for feature extraction. Classification was performed using a Support Vector Machine (SVM) using a Radial Basis Function (RBF). Classification accuracies in the range 80-90% were achieved to separate the three movements mentioned.

AB - This paper presents the results of our experimental investigation into how different environments impact the classification of human motion using radar micro-Doppler (MD) signatures. The environments studied include free space, through-thewall, leaf tree foliage, and needle tree foliage. Results on presented on classification of the following three motions: crawling, walking, and jogging. The classification task was designed how to best separate these movements. The human motion data were acquired using a monostatic coherent Doppler radar operating in the C-band at 6.5 GHz from a total of six human subjects. The received signals were analyzed in the time-frequency domain using the Short-time Fourier Transform (STFT) which was used for feature extraction. Classification was performed using a Support Vector Machine (SVM) using a Radial Basis Function (RBF). Classification accuracies in the range 80-90% were achieved to separate the three movements mentioned.

UR - http://www.scopus.com/inward/record.url?scp=84982309247&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84982309247&partnerID=8YFLogxK

U2 - 10.1117/12.2228397

DO - 10.1117/12.2228397

M3 - Conference contribution

AN - SCOPUS:84982309247

VL - 9829

BT - Radar Sensor Technology XX

A2 - Doerry, Armin

A2 - Ranney, Kenneth I.

PB - SPIE

ER -

Zenaldin M, Narayanan RM. Radar micro-Doppler based human activity classification for indoor and outdoor environments. In Doerry A, Ranney KI, editors, Radar Sensor Technology XX. Vol. 9829. SPIE. 2016. 98291B https://doi.org/10.1117/12.2228397