时频分布重排方法在水下目标回声识别中的应用

特征提取是目标识别的关键技术,本文提出了一种基于时频分布重排的Wigner-Ville分布(WD)特征提取方法。选择WD作为研究问题的切入点,使用核函数方法,通过平滑伪Wigner-Ville分布(SPWD)抑制交叉项;为解决引入核函数导致信号时频聚集性下降问题,我们采用时频重排方法来增强目标的时频聚集性,最后用海上实验数据对本文方法进行了有效性检验。实验结果表明,本文提出的SPWD时频重排特征提取方法具有:(1)可有效抑制WD固有的交叉项;(2)增强目标回声信号时频聚集性;(3)可明显地提高水下目标识别率。该方法具有一定的应用推广价值,为解决水下目标识别问题提供了很好的思路。

Application of time-frequency distribution reassignment method to underwater target echo classification

Feature extraction is a key technology for target classification. In this paper a Wigner-Ville distribution feature extraction method based on time-frequency reassignment theory is proposed. The breakthrough point of the research problem is WD. The kernel function method and the smoothed pseudo Wigner-Ville distribution(SPWD) are used to restrain the cross items. To solve the problem of which the kernel function method may cause signal time-frequency aggregation to decrease, a time-frequency distribution reassignment method is applied to enhance the target time-frequency aggregation. Finally, the effectiveness of the method is testified by sea experiment data. The experimental results show that the advantages of SPWD time-frequency distribution reassignment feature extraction method are as follows: (1)restraining the cross items more effectively; (2)enhancing target echo time-frequency aggregation; (3)increasing target classification rate. This paper provides a good method for underwater target classification which has promising application prospects.