Recurrent neural network for high-resolution radar ship target recognition

Author

Feixue, Wang ; Wenxian, Yu ; Guirong, Guo

Author_Institution

Autom. Target Recognition Lab., Nat. Univ. of Defense Technol., Changsha, China

fYear

1996

fDate

8-10 Oct 1996

Firstpage

200

Lastpage

203

Abstract

The high-resolution radar waveform describes the amplitude of targets´ multiple scattering centers and their distribution in the radial axis. As viewed from the time domain, the target waveform can also be regarded as a time sequence such that it can be classified using recurrent neural networks (RNN) which are suitable for time sequence processing. A modified partially RNN and its algorithm are proposed. This method reaches an average recognition rate of above 90% for 8 class high-resolution radar targets, and it is tolerant of time shift to a certain degree

Keywords

backpropagation; feedforward neural nets; radar computing; radar cross-sections; radar signal processing; radar target recognition; recurrent neural nets; ships; signal resolution; time-domain analysis; algorithm; average recognition rate; backpropagation; distribution; feedforward neural network; high-resolution radar ship target recognition; high-resolution radar waveform; modified partially recurrent neural network; multiple scattering centers; radial axis; target amplitude; target waveform; time sequence processing; time shift; Artificial intelligence; Artificial neural networks; Delay effects; Laboratories; Marine vehicles; Pattern recognition; Radar scattering; Radar theory; Recurrent neural networks; Target recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Radar, 1996. Proceedings., CIE International Conference of

Conference_Location

Beijing

Print_ISBN

0-7803-2914-7

Type

conf

DOI

10.1109/ICR.1996.573806

Filename

573806