有源声呐回波二维匹配滤波特征提取及分类检测  

Two-dimensional matched filtering feature extraction and classification detection of active sonar echo

作　　者：赵猛 王文博[1,2,3] 任群言 肖旭 马力 余赟[4] ZHAO Meng;WANG Wenbo;REN Qunyan;XIAO Xu;MA Li;YU Yun(Institute of Acoustics,Chinese Academy of Sciences,Beijing,100190;Key Laboratory of Underwater Acoustic Environment,Chinese Academy of Sciences,Beijing,100190;University of Chinese Academy of Sciences,Beijing,100049;People’s Liberation Army of China,Naval Research Academy,Beijing,100161)

机构地区：[1]中国科学院声学研究所,北京100190 [2]中国科学院水声环境特性重点实验室,北京100190 [3]中国科学院大学,北京100049 [4]中国人民解放军海军研究院,北京100161

出　　处：《声学学报》2024年第4期731-742,共12页Acta Acustica

基　　金：国家自然科学基金项目(12204506);中国科学院声学研究所自主部署项目(MBDX202102)资助。

摘　　要：为降低有源声呐回波检测中的杂波虚警,提升低虚警率下的目标回波检测率,提出了一种基于二维匹配滤波的有源声呐回波分类检测方法。该方法将有源声呐接收数据的匹配信号划分为多个脉宽合适的子信号,并利用各子信号分别对接收数据进行匹配滤波处理,提取能够同时联合时频信息和匹配增益的二维匹配滤波特征。同时,选择卷积神经网络作为回波分类检测器,基于获取的二维匹配滤波特征区分回波信号和杂波信号。仿真和实验结果表明,该方法可提升浅海信道下的低虚警回波检测能力,在1‰虚警率下的海上回波检测率达到91.30%,相比已有方法提升4%左右。To reduce the clutter false alarm in active sonar echo detection,and enhance the echo detection rate while maintaining a low false alarm rate,a classification detection method based on the two-dimensional matching filter(2D-MF)is proposed.This method divides the matched signal into multiple sub-signals with appropriate pulse widths,and the sub-signals are used to respectively perform the matched filtering and extract the 2D-MF features from the active sonar received data.The extracted 2D-MF features utilize the time-frequency information and matching gain simultaneously.The convolutional neural network is then employed as the echo detector,effectively distinguishing between echo signals and clutter signals.Simulation and experimental results demonstrate that this method significantly improves the echo detection rate while maintaining a low false alarm rate in shallow-water channels.Specifically,it achieves an echo detection rate of 91.30%with a false alarm rate of 1‰for the at-sea measured data,representing an approximate 4%improvement compared to existing methods.

关 键 词：回波检测 杂波信号 低虚警 二维匹配滤波 卷积神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TB56[自动化与计算机技术—控制科学与工程]