Multi-to-two-LDA for HRRP radar target recognition

Lu Yao, Lei Han, Jindong Guo, Tao Shang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

High resolution range profile (HRRP) plays an important role in the field of radar automatic target recognition (RATR). In order to overcome the shortcoming of serious degradation in accuracy when processing a multi-target-recognition problem with LDA, this paper proposes a novel method named multi-to-two-LDA (MTTL), which can transform a problem of multi-target-recognition into a series of two-target recognition problems. The input data is 14 different features extracted from 3 targets' HRRPs. After a multi-target-recognition problem is converted into 3 two-target-recognition problems, LDA processing is performed immediately, and followed corresponding Bayes classifiers are trained. Experimental results show that the proposed method does not only improve the recognition accuracy greatly when dealing with a multi-target-recognition problem, but also keep a high and stable recognition performance under the condition of using few training samples.

Original languageEnglish
Title of host publicationICSIDP 2019 - IEEE International Conference on Signal, Information and Data Processing 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728123455
DOIs
Publication statusPublished - Dec 2019
Event2019 IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2019 - Chongqing, China
Duration: 11 Dec 201913 Dec 2019

Publication series

NameICSIDP 2019 - IEEE International Conference on Signal, Information and Data Processing 2019

Conference

Conference2019 IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2019
Country/TerritoryChina
CityChongqing
Period11/12/1913/12/19

Keywords

  • HRRP
  • LDA
  • MTTL
  • recognition

Fingerprint

Dive into the research topics of 'Multi-to-two-LDA for HRRP radar target recognition'. Together they form a unique fingerprint.

Cite this