Micro-Doppler based target classification using multi-feature integration

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

doi:10.1049/cp.2013.2042

Micro-Doppler based target classification using multi-feature integration

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

Electronic And Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

15 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.

Original language	English
Title of host publication	IET Intelligent Signal Processing Conference 2013 (ISP 2013)
Number of pages	6
DOIs	https://doi.org/10.1049/cp.2013.2042
Publication status	Published - 2013
Event	IET Intelligent Signal Processing Conference - London, United Kingdom Duration: 2 Dec 2013 → 3 Dec 2013

Conference

Conference	IET Intelligent Signal Processing Conference
Country/Territory	United Kingdom
City	London
Period	2/12/13 → 3/12/13

Keywords

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

Access to Document

10.1049/cp.2013.2042

Cite this

@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)",

note = "IET Intelligent Signal Processing Conference ; Conference date: 02-12-2013 Through 03-12-2013",

}

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)

T2 - IET Intelligent Signal Processing Conference

Y2 - 2 December 2013 through 3 December 2013

ER -

Micro-Doppler based target classification using multi-feature integration

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this