The modification of intelligent target detection in nonstationary clutter

Author

Xiaoyan, Ma ; Chunxia, Li ; Xianda, Zhang

Author_Institution

Tsinghua Univ., Beijing, China

fYear

2001

fDate

2001

Firstpage

324

Lastpage

328

Abstract

In non-stationary background, like sea clutter, the intelligent detection method independent of the statistical model, has the obvious advantages. Based on the strategy by Haykin (1997), a new intelligent detection scheme is proposed to improve the detection performance, in which the Kohonen neural network (NN) and the modified fuzzy NN are used. A variety of comparison experiments have been done with both the simulated data and the real sea clutter data between our proposed scheme and Haykin´s scheme, which show clearly our method has a higher detection ability and a lower false-alarm rate

Keywords

feature extraction; fuzzy neural nets; radar clutter; radar computing; radar detection; self-organising feature maps; Kohonen neural network; MLP; PCA neural network; detection performance; false-alarm rate; feature extraction network; intelligent target detection; modified fuzzy neural network; modular learning strategy; multilayer perception; nonstationary background; nonstationary clutter; radar signal detection; real sea clutter data; sea clutter; self-organizing feature map; simulated data; statistical model; Feature extraction; Fuzzy neural networks; Neural networks; Object detection; Principal component analysis; Radar clutter; Radar detection; Radar signal processing; Signal detection; Signal resolution;

fLanguage

English

Publisher

ieee

Conference_Titel

Radar, 2001 CIE International Conference on, Proceedings

Conference_Location

Beijing

Print_ISBN

0-7803-7000-7

Type

conf

DOI

10.1109/ICR.2001.984683

Filename

984683