Analytic radar micro-Doppler signatures classification

Beom Seok Oh, Zhaoning Gu, Guan Wang, Kar Ann Toh, Zhiping Lin

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

Abstract

Due to its capability of capturing the kinematic properties of a target object, radar micro-Doppler signatures (m-DS) play an important role in radar target classification. This is particularly evident from the remarkable number of research papers published every year on m-DS for various applications. However, most of these works rely on the support vector machine (SVM) for target classification. It is well known that training an SVM is computationally expensive due to its nature of search to locate the supporting vectors. In this paper, the classifier learning problem is addressed by a total error rate (TER) minimization where an analytic solution is available. This largely reduces the search time in the learning phase. The analytically obtained TER solution is globally optimal with respect to the classification total error count rate. Moreover, our empirical results show that TER outperforms SVM in terms of classification accuracy and computational efficiency on a five-category radar classification problem.

Original languageEnglish
Title of host publicationSecond International Workshop on Pattern Recognition
PublisherSPIE
Volume10443
ISBN (Electronic)9781510613508
DOIs
Publication statusPublished - 2017 Jan 1
Event2nd International Workshop on Pattern Recognition, IWPR 2017 - Singapore, Singapore
Duration: 2017 May 12017 May 3

Other

Other2nd International Workshop on Pattern Recognition, IWPR 2017
CountrySingapore
CitySingapore
Period17/5/117/5/3

Fingerprint

Doppler
Radar
radar
Signature
signatures
Error Rate
Support Vector Machine
Support vector machines
Target
learning
radar targets
Analytic Solution
Classification Problems
Computational Efficiency
Kinematics
Count
classifiers
Computational efficiency
Classifier
Classifiers

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

Oh, B. S., Gu, Z., Wang, G., Toh, K. A., & Lin, Z. (2017). Analytic radar micro-Doppler signatures classification. In Second International Workshop on Pattern Recognition (Vol. 10443). [104431L] SPIE. https://doi.org/10.1117/12.2280299
Oh, Beom Seok ; Gu, Zhaoning ; Wang, Guan ; Toh, Kar Ann ; Lin, Zhiping. / Analytic radar micro-Doppler signatures classification. Second International Workshop on Pattern Recognition. Vol. 10443 SPIE, 2017.
@inproceedings{a03f0bee015c4c6b9b20fe6b986d3f05,
title = "Analytic radar micro-Doppler signatures classification",
abstract = "Due to its capability of capturing the kinematic properties of a target object, radar micro-Doppler signatures (m-DS) play an important role in radar target classification. This is particularly evident from the remarkable number of research papers published every year on m-DS for various applications. However, most of these works rely on the support vector machine (SVM) for target classification. It is well known that training an SVM is computationally expensive due to its nature of search to locate the supporting vectors. In this paper, the classifier learning problem is addressed by a total error rate (TER) minimization where an analytic solution is available. This largely reduces the search time in the learning phase. The analytically obtained TER solution is globally optimal with respect to the classification total error count rate. Moreover, our empirical results show that TER outperforms SVM in terms of classification accuracy and computational efficiency on a five-category radar classification problem.",
author = "Oh, {Beom Seok} and Zhaoning Gu and Guan Wang and Toh, {Kar Ann} and Zhiping Lin",
year = "2017",
month = "1",
day = "1",
doi = "10.1117/12.2280299",
language = "English",
volume = "10443",
booktitle = "Second International Workshop on Pattern Recognition",
publisher = "SPIE",
address = "United States",

}

Oh, BS, Gu, Z, Wang, G, Toh, KA & Lin, Z 2017, Analytic radar micro-Doppler signatures classification. in Second International Workshop on Pattern Recognition. vol. 10443, 104431L, SPIE, 2nd International Workshop on Pattern Recognition, IWPR 2017, Singapore, Singapore, 17/5/1. https://doi.org/10.1117/12.2280299

Analytic radar micro-Doppler signatures classification. / Oh, Beom Seok; Gu, Zhaoning; Wang, Guan; Toh, Kar Ann; Lin, Zhiping.

Second International Workshop on Pattern Recognition. Vol. 10443 SPIE, 2017. 104431L.

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

TY - GEN

T1 - Analytic radar micro-Doppler signatures classification

AU - Oh, Beom Seok

AU - Gu, Zhaoning

AU - Wang, Guan

AU - Toh, Kar Ann

AU - Lin, Zhiping

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Due to its capability of capturing the kinematic properties of a target object, radar micro-Doppler signatures (m-DS) play an important role in radar target classification. This is particularly evident from the remarkable number of research papers published every year on m-DS for various applications. However, most of these works rely on the support vector machine (SVM) for target classification. It is well known that training an SVM is computationally expensive due to its nature of search to locate the supporting vectors. In this paper, the classifier learning problem is addressed by a total error rate (TER) minimization where an analytic solution is available. This largely reduces the search time in the learning phase. The analytically obtained TER solution is globally optimal with respect to the classification total error count rate. Moreover, our empirical results show that TER outperforms SVM in terms of classification accuracy and computational efficiency on a five-category radar classification problem.

AB - Due to its capability of capturing the kinematic properties of a target object, radar micro-Doppler signatures (m-DS) play an important role in radar target classification. This is particularly evident from the remarkable number of research papers published every year on m-DS for various applications. However, most of these works rely on the support vector machine (SVM) for target classification. It is well known that training an SVM is computationally expensive due to its nature of search to locate the supporting vectors. In this paper, the classifier learning problem is addressed by a total error rate (TER) minimization where an analytic solution is available. This largely reduces the search time in the learning phase. The analytically obtained TER solution is globally optimal with respect to the classification total error count rate. Moreover, our empirical results show that TER outperforms SVM in terms of classification accuracy and computational efficiency on a five-category radar classification problem.

UR - http://www.scopus.com/inward/record.url?scp=85028559363&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028559363&partnerID=8YFLogxK

U2 - 10.1117/12.2280299

DO - 10.1117/12.2280299

M3 - Conference contribution

AN - SCOPUS:85028559363

VL - 10443

BT - Second International Workshop on Pattern Recognition

PB - SPIE

ER -

Oh BS, Gu Z, Wang G, Toh KA, Lin Z. Analytic radar micro-Doppler signatures classification. In Second International Workshop on Pattern Recognition. Vol. 10443. SPIE. 2017. 104431L https://doi.org/10.1117/12.2280299