基于离散小波变换的水下回波信号尾波包络特征提取

Tail-Wave Envelop Feature Extraction of an Underwater Echo Based on Discrete Wavelet Transform

提出一种水下目标回波的特征提取方法.该方法在离散小波变换的基础上,基于回波信号中的散射成分可以对水下底质进行分类的理论基础,提取水下回波信号尾波包络特征作为识别特征矢量,构成基于尾波包络特征的特征空间,再采用最佳鉴别矢量法将特征空间进行特征压缩,最后利用最小距离分类器对目标回波进行分类.实测数据结果表明,采用这种方法得到的包络特征是一种稳健、有效的特征,能够获得较高的正确识别率.

A feature extraction method of underwater target echo is proposed based on discrete wavelet transform. In the method, these tail-wave envelop features of an underwater echo which compose the feature space are extracted as the discriminating eigenvectors and compressed with optimal set of discriminant vectors. At the end, the classification is accomplished of target echo using the shortest-distance classifier. The result of experimentation data shows that the envelop feature acquired with this method is a kind of robust and effective feature to recognize the kind of underwater echoes, and high recognition rate can be obtained.