一种应用于水声目标检测的盲源分离算法  

Blind Separation Algorithm for Underwater Target Detection

作　　者：理华[1,2] 郝程鹏[1] 侯朝焕[1] 马晓川[1] 杨俊[1,2] 

机构地区：[1]中国科学院声学研究所,北京100190 [2]中国科学院研究生院,北京100039

出　　处：《数据采集与处理》2008年第B09期6-11,共6页Journal of Data Acquisition and Processing

摘　　要：提出了一种新的盲源分离方法。该方法基于独立分量(ICA)理论,可以有效去除噪声,提高目标检测的性能。针对在盲源分离中噪声消除比较困难这一问题,利用水声信号半盲的特点,引入了虚拟信号的概念。通过添加虚拟信号,成功地分离了混合信号。高斯噪声和K分布噪声的仿真表明,该算法在强背景噪声下较匹配滤波算法有明显的检测优势。An algorithm for blind separation of sources is proposed. The algorithm based on the independent component analysis （ICA） theory can reduce the noise and improve the detection performance. Aimed at the problem difficult to eliminate the noise, the virtual signal is proposed and applied to the ICA algorithm for underwater target detection by using half-blind acoustic characteristics. The mixed signals can be separated by adding the virtual signal. Simulation results indicate that the algorithm performs better than the match filter method in strong background noise, such as the Gauss distribution and the K distribution noises.

关 键 词：目标检测 盲源分离 独立分量分析 水下目标检测 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] N941.5[自动化与计算机技术—计算机科学与技术]