The modification of intelligent target detection in nonstationary clutter

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.