Satellite target recognition algorithm based on BP neural networks

Xiankang Liu*, Meiguo Gao, Xiongjun Fu

*Corresponding author for this work

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

2 Citations (Scopus)

Abstract

For high resolution range profile (HRRP) is sensitive to pose and translation, Back-Propogation (BP) algorithm is proposed to be used to process even rank central moments of HRRP in target recognition. Wavelet denoising is used to enhance the signal noise rate (SNR) of HRRP. Then central moments are extracted from the denoised HRRP. Even rank central moments can be used as features for target recognition because they are more stable and the dimension is reduced. BP algorithm is used to process the central moments feature vector. The experimental results based on real satellites data show that the proposed method achieves good recognition performance based on its low storage and computational complexity.

Original languageEnglish
Title of host publicationICIEA 2007
Subtitle of host publication2007 Second IEEE Conference on Industrial Electronics and Applications
Pages1775-1778
Number of pages4
DOIs
Publication statusPublished - 2007
Event2007 2nd IEEE Conference on Industrial Electronics and Applications, ICIEA 2007 - Harbin, China
Duration: 23 May 200725 May 2007

Publication series

NameICIEA 2007: 2007 Second IEEE Conference on Industrial Electronics and Applications

Conference

Conference2007 2nd IEEE Conference on Industrial Electronics and Applications, ICIEA 2007
Country/TerritoryChina
CityHarbin
Period23/05/0725/05/07

Keywords

  • BP neural networks
  • Central moments
  • High resolution range profiles

Fingerprint

Dive into the research topics of 'Satellite target recognition algorithm based on BP neural networks'. Together they form a unique fingerprint.

Cite this