基于时变AR预白滤波处理的水雷非水雷识别算法

Classification Algorithm of Torpedo Based on Autoregressive Malel

基于时变AR预白化滤波器处理方法采用图象模式识别技术设计开发了一个水雷/非水雷的自动识别系统。数据预处理完成后截取有效数据段并提取信号特征由分类器对真假水雷目标进行识别。时变AR预白滤波器方法在一定程度上将背景混响预白化,提高了匹配滤波的检测性能。本文基于实际湖试和海试数据对该识别算法进行验证,结果表明此算法识别效果较好。

In this paper, A classification algorithm of underwater objects by pattern -recognition technique with autoregressive model prewhitening filter is designed. In short, some features are extracted from the Wigner - Ville distribution and the bispectrum of partially overlapped short segments of the preprocessed echo signal. The preprocessing is composed of an adaptive prewhitening filter and a bank of matched filters. The autoregressive parameters are computed by algorithms based on the higher - order statistics. The examination resuit yielded by the described technique are impressive.