基于小波包和1(1/2)维谱的舰船辐射噪声频域特征提取及融合

Extraction and fusion of frequency-domain features from ship radiated-noise based on wavelet packet and 1(1/2)-dimensional spectrum

摘要: 舰船辐射噪声频域特征提取是舰船目标识别的关键技术之一。为提高舰船目标识别率,采用小波包和1(1/2)维谱对舰船辐射噪声进行多小波包空间调制谱和噪声谱特征提取及融合研究。并用提取的特征对五类舰船目标辐射噪声进行了分类识别实验,结果表明所提特征具有很好的分类识别效果。

Abstract: Extraction of frequency-domain features from ship radiated-noise is a key technique in ship-target recognition. To improve the recognition-rate, feature extraction in the frequency-domain is first studied based on wavelet packet analysis and 1-dimensional spectrum. Frequency-domain feature fusion is then investigated. An experiment is carried out to classify five different classes of ship-targets, giving satisfactory results.