Micro-Doppler based target classification using multi-feature integration

A W Miller, C Clemente, A Robinson, D Greig, A M. Kinghorn, J J. Soraghan

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

7 Citations (Scopus)

Abstract

Three novel micro-Doppler feature extraction algorithms are presented and applied to a dataset containing real X-band radar data of moving ground targets. In each case data dimensional reduction was carried out using principal component analysis (PCA) and incorporated into the feature extraction process. Extracted features are classified using a support vector machine (SVM) classifier. It was found that all three algorithms were able to produce classification accuracies in excess of 90%. The performance of the different algorithms are shown to depend on the method used and the degree of dimensionality reduction imposed at the PCA stage.
LanguageEnglish
Title of host publicationIET Intelligent Signal Processing Conference 2013 (ISP 2013)
Number of pages6
DOIs
Publication statusPublished - 2013
EventIET Intelligent Signal Processing Conference - London, United Kingdom
Duration: 2 Dec 20133 Dec 2013

Conference

ConferenceIET Intelligent Signal Processing Conference
CountryUnited Kingdom
CityLondon
Period2/12/133/12/13

Fingerprint

Principal component analysis
Feature extraction
Support vector machines
Radar
Classifiers

Keywords

  • micro doppler
  • target classification
  • robust principal component analysis
  • minimum covariance determinant
  • support vector machine classification

Cite this

Miller, A. W., Clemente, C., Robinson, A., Greig, D., Kinghorn, A. M., & Soraghan, J. J. (2013). Micro-Doppler based target classification using multi-feature integration. In IET Intelligent Signal Processing Conference 2013 (ISP 2013) https://doi.org/10.1049/cp.2013.2042
Miller, A W ; Clemente, C ; Robinson, A ; Greig, D ; Kinghorn, A M. ; Soraghan, J J. / Micro-Doppler based target classification using multi-feature integration. IET Intelligent Signal Processing Conference 2013 (ISP 2013). 2013.
@inproceedings{1cce668c6f334c048d1007ab773434c9,
title = "Micro-Doppler based target classification using multi-feature integration",
abstract = "Three novel micro-Doppler feature extraction algorithms are presented and applied to a dataset containing real X-band radar data of moving ground targets. In each case data dimensional reduction was carried out using principal component analysis (PCA) and incorporated into the feature extraction process. Extracted features are classified using a support vector machine (SVM) classifier. It was found that all three algorithms were able to produce classification accuracies in excess of 90{\%}. The performance of the different algorithms are shown to depend on the method used and the degree of dimensionality reduction imposed at the PCA stage.",
keywords = "micro doppler, target classification, robust principal component analysis, minimum covariance determinant , support vector machine classification",
author = "Miller, {A W} and C Clemente and A Robinson and D Greig and Kinghorn, {A M.} and Soraghan, {J J.}",
year = "2013",
doi = "10.1049/cp.2013.2042",
language = "English",
isbn = "978-1-84919-774-8",
booktitle = "IET Intelligent Signal Processing Conference 2013 (ISP 2013)",

}

Miller, AW, Clemente, C, Robinson, A, Greig, D, Kinghorn, AM & Soraghan, JJ 2013, Micro-Doppler based target classification using multi-feature integration. in IET Intelligent Signal Processing Conference 2013 (ISP 2013). IET Intelligent Signal Processing Conference, London, United Kingdom, 2/12/13. https://doi.org/10.1049/cp.2013.2042

Micro-Doppler based target classification using multi-feature integration. / Miller, A W; Clemente, C; Robinson, A; Greig, D; Kinghorn, A M.; Soraghan, J J.

IET Intelligent Signal Processing Conference 2013 (ISP 2013). 2013.

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

TY - GEN

T1 - Micro-Doppler based target classification using multi-feature integration

AU - Miller, A W

AU - Clemente, C

AU - Robinson, A

AU - Greig, D

AU - Kinghorn, A M.

AU - Soraghan, J J.

PY - 2013

Y1 - 2013

N2 - Three novel micro-Doppler feature extraction algorithms are presented and applied to a dataset containing real X-band radar data of moving ground targets. In each case data dimensional reduction was carried out using principal component analysis (PCA) and incorporated into the feature extraction process. Extracted features are classified using a support vector machine (SVM) classifier. It was found that all three algorithms were able to produce classification accuracies in excess of 90%. The performance of the different algorithms are shown to depend on the method used and the degree of dimensionality reduction imposed at the PCA stage.

AB - Three novel micro-Doppler feature extraction algorithms are presented and applied to a dataset containing real X-band radar data of moving ground targets. In each case data dimensional reduction was carried out using principal component analysis (PCA) and incorporated into the feature extraction process. Extracted features are classified using a support vector machine (SVM) classifier. It was found that all three algorithms were able to produce classification accuracies in excess of 90%. The performance of the different algorithms are shown to depend on the method used and the degree of dimensionality reduction imposed at the PCA stage.

KW - micro doppler

KW - target classification

KW - robust principal component analysis

KW - minimum covariance determinant

KW - support vector machine classification

U2 - 10.1049/cp.2013.2042

DO - 10.1049/cp.2013.2042

M3 - Conference contribution book

SN - 978-1-84919-774-8

BT - IET Intelligent Signal Processing Conference 2013 (ISP 2013)

ER -

Miller AW, Clemente C, Robinson A, Greig D, Kinghorn AM, Soraghan JJ. Micro-Doppler based target classification using multi-feature integration. In IET Intelligent Signal Processing Conference 2013 (ISP 2013). 2013 https://doi.org/10.1049/cp.2013.2042