基于峰度偏度和WD-LDA的飞机目标分类方法

目前,多数的喷气发动机调制特征提取方法都是基于调制波的周期或调制线谱的谱间间隔,但该类谱估计方法往往受信噪比、脉冲重复频率及观测时间影响很难获得很好的分类性能。文中对三类飞机目标回波进行统计分析发现,其归一化幅度分布存在明显差异,据此创造性地提取出峰度偏度特征,并结合小波分解-线性判别分析处理,对目标进行分类。该特征具有很强的抗噪声能力,对脉冲重复频率和观测时间要求不高,且可通过其中一个参数去弥补另一个参数。仿真实验证明了所提方法具有很好的分类性能。

Aircraft Target Classification Method Based on Kurtosis-skewness and WD-LDA

At present, most of the jet engine modulation feature extraction methods are based on the modulation wave period or the inter-spectural interval of the modulation line spectrum. However, such spectral estimation methods are often difficult to obtain good classification performance due to the signal to noise ratio, pulse repetition frequency(PRF), and observation time. Statistical analysis of the three types of aircraft target echoes show that there is a signitficant difference in the normalized amplitude distribution, so kurtosis-skewness feature is creatively proposed and combined with wavelet decomposition-linear discriminant analysis processing, to classify the targets. This feature has a strong anti-noise capability, the requirement for PRF and observation time is not high, and one of the parameters can be used to make up for another paramter. It has been proved by the simulation test that the proposed method has good classification performance.