Performance analysis of co-located and distributed MIMO radar for micro-doppler classification

Mustafa Bugra Ozcan, Sevgi Zubeyde Gurbuz, Adriano Rosario Persico, Carmine Clemente, John Soraghan

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

Over the past few years, the use of Multiple Input Multiple Output (MIMO) radar has gained increased attention as a way to mitigate the degredation of micro-Doppler classification performance incurred when the aspect angle approaches 90 degrees. In this work, the efficacy of co-located MIMO radar is compared with that of distributed MIMO. The performance anaylsis is accomplished for three different classification problems: 1) discrimination of a walking group of people from a running group of people; 2) identification of individual human activities, and 3) classification of different types of walking. In the co-located configuration each radar is placed side by side so as to form a line. In the distributed configuration, the radar positions are separated to observe the subjects from different angles. Starting from the cadence velocity diagram (CVD), the Pseudo-Zernike moments based features are extracted because of their robustness with respect to unwanted scalar and angular dependencies. Two different approaches to integrate the features obtained from multi-aspect data are compared: concatenation and principal component analysis (PCA). Results show that a distributed MIMO configuration and use of PCA to fuse multiperspective features yields higher classification performance as compared to a co-located configuration or feature vector concatenation.
LanguageEnglish
Pages1-4
Number of pages4
Publication statusPublished - 7 Oct 2016
EventEuropean Radar Conference 2016, EuRAD 2016 - London, United Kingdom
Duration: 3 Oct 20167 Oct 2016

Conference

ConferenceEuropean Radar Conference 2016, EuRAD 2016
Abbreviated titleEuRAD 2016
CountryUnited Kingdom
CityLondon
Period3/10/167/10/16

Fingerprint

MIMO (control systems)
radar
Radar
walking
principal components analysis
configurations
Principal component analysis
fuses
Electric fuses
discrimination
diagrams
scalars
moments

Keywords

  • MIMO radar
  • micro-doppler classification
  • distributed MIMO
  • co-located MIMO

Cite this

Bugra Ozcan, M., Gurbuz, S. Z., Persico, A. R., Clemente, C., & Soraghan, J. (2016). Performance analysis of co-located and distributed MIMO radar for micro-doppler classification. 1-4. Paper presented at European Radar Conference 2016, EuRAD 2016, London, United Kingdom.
Bugra Ozcan, Mustafa ; Gurbuz, Sevgi Zubeyde ; Persico, Adriano Rosario ; Clemente, Carmine ; Soraghan, John. / Performance analysis of co-located and distributed MIMO radar for micro-doppler classification. Paper presented at European Radar Conference 2016, EuRAD 2016, London, United Kingdom.4 p.
@conference{f5ae206893d64881bd6c6ae081cc295e,
title = "Performance analysis of co-located and distributed MIMO radar for micro-doppler classification",
abstract = "Over the past few years, the use of Multiple Input Multiple Output (MIMO) radar has gained increased attention as a way to mitigate the degredation of micro-Doppler classification performance incurred when the aspect angle approaches 90 degrees. In this work, the efficacy of co-located MIMO radar is compared with that of distributed MIMO. The performance anaylsis is accomplished for three different classification problems: 1) discrimination of a walking group of people from a running group of people; 2) identification of individual human activities, and 3) classification of different types of walking. In the co-located configuration each radar is placed side by side so as to form a line. In the distributed configuration, the radar positions are separated to observe the subjects from different angles. Starting from the cadence velocity diagram (CVD), the Pseudo-Zernike moments based features are extracted because of their robustness with respect to unwanted scalar and angular dependencies. Two different approaches to integrate the features obtained from multi-aspect data are compared: concatenation and principal component analysis (PCA). Results show that a distributed MIMO configuration and use of PCA to fuse multiperspective features yields higher classification performance as compared to a co-located configuration or feature vector concatenation.",
keywords = "MIMO radar, micro-doppler classification, distributed MIMO, co-located MIMO",
author = "{Bugra Ozcan}, Mustafa and Gurbuz, {Sevgi Zubeyde} and Persico, {Adriano Rosario} and Carmine Clemente and John Soraghan",
year = "2016",
month = "10",
day = "7",
language = "English",
pages = "1--4",
note = "European Radar Conference 2016, EuRAD 2016, EuRAD 2016 ; Conference date: 03-10-2016 Through 07-10-2016",

}

Bugra Ozcan, M, Gurbuz, SZ, Persico, AR, Clemente, C & Soraghan, J 2016, 'Performance analysis of co-located and distributed MIMO radar for micro-doppler classification' Paper presented at European Radar Conference 2016, EuRAD 2016, London, United Kingdom, 3/10/16 - 7/10/16, pp. 1-4.

Performance analysis of co-located and distributed MIMO radar for micro-doppler classification. / Bugra Ozcan, Mustafa; Gurbuz, Sevgi Zubeyde; Persico, Adriano Rosario; Clemente, Carmine; Soraghan, John.

2016. 1-4 Paper presented at European Radar Conference 2016, EuRAD 2016, London, United Kingdom.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Performance analysis of co-located and distributed MIMO radar for micro-doppler classification

AU - Bugra Ozcan, Mustafa

AU - Gurbuz, Sevgi Zubeyde

AU - Persico, Adriano Rosario

AU - Clemente, Carmine

AU - Soraghan, John

PY - 2016/10/7

Y1 - 2016/10/7

N2 - Over the past few years, the use of Multiple Input Multiple Output (MIMO) radar has gained increased attention as a way to mitigate the degredation of micro-Doppler classification performance incurred when the aspect angle approaches 90 degrees. In this work, the efficacy of co-located MIMO radar is compared with that of distributed MIMO. The performance anaylsis is accomplished for three different classification problems: 1) discrimination of a walking group of people from a running group of people; 2) identification of individual human activities, and 3) classification of different types of walking. In the co-located configuration each radar is placed side by side so as to form a line. In the distributed configuration, the radar positions are separated to observe the subjects from different angles. Starting from the cadence velocity diagram (CVD), the Pseudo-Zernike moments based features are extracted because of their robustness with respect to unwanted scalar and angular dependencies. Two different approaches to integrate the features obtained from multi-aspect data are compared: concatenation and principal component analysis (PCA). Results show that a distributed MIMO configuration and use of PCA to fuse multiperspective features yields higher classification performance as compared to a co-located configuration or feature vector concatenation.

AB - Over the past few years, the use of Multiple Input Multiple Output (MIMO) radar has gained increased attention as a way to mitigate the degredation of micro-Doppler classification performance incurred when the aspect angle approaches 90 degrees. In this work, the efficacy of co-located MIMO radar is compared with that of distributed MIMO. The performance anaylsis is accomplished for three different classification problems: 1) discrimination of a walking group of people from a running group of people; 2) identification of individual human activities, and 3) classification of different types of walking. In the co-located configuration each radar is placed side by side so as to form a line. In the distributed configuration, the radar positions are separated to observe the subjects from different angles. Starting from the cadence velocity diagram (CVD), the Pseudo-Zernike moments based features are extracted because of their robustness with respect to unwanted scalar and angular dependencies. Two different approaches to integrate the features obtained from multi-aspect data are compared: concatenation and principal component analysis (PCA). Results show that a distributed MIMO configuration and use of PCA to fuse multiperspective features yields higher classification performance as compared to a co-located configuration or feature vector concatenation.

KW - MIMO radar

KW - micro-doppler classification

KW - distributed MIMO

KW - co-located MIMO

UR - http://www.eumweek.com/conferences/eurad.html

M3 - Paper

SP - 1

EP - 4

ER -

Bugra Ozcan M, Gurbuz SZ, Persico AR, Clemente C, Soraghan J. Performance analysis of co-located and distributed MIMO radar for micro-doppler classification. 2016. Paper presented at European Radar Conference 2016, EuRAD 2016, London, United Kingdom.