刘桐1,
杨阳2
1.杭州电子科技大学自动化学院 杭州 310018
2.上海交通大学船舶海洋与建筑工程学院 上海 201100
基金项目:水下测控技术重点实验室延伸性基金(JCKYS2018207050)
详细信息
作者简介:孙同晶：女，1978年生，博士，副教授，研究方向为主动声呐目标回波信号处理、信息融合和模式识别
刘桐：男，1996年生，硕士生，研究方向为主动声呐目标分类识别方法
杨阳：女，1986年生，博士后，讲师，研究方向为海洋环境下目标特征提取和分类识别
通讯作者:孙同晶 stj@hdu.edu.cn
中图分类号:TN911.7计量
文章访问数:388
HTML全文浏览量:124
PDF下载量:37
被引次数:0
出版历程
收稿日期:2020-07-30
修回日期:2021-02-08
网络出版日期:2021-02-18
刊出日期:2021-03-22
Sparse Representation Classification Method for Active Sonar Target Based on Multi-order Fractional Fourier Domain Feature Fusion
Tongjing SUN1,,,Tong LIU1,
Yang YANG2
1. Automation Department, Hangzhou Dianzi University, Hangzhou 310018, China
2. School of Naval Architecture, Ocean & Civil Engineering, Shanghai Jiao Tong University, Shanghai 201100, China
Funds:The Extension Fund from Underwater Test and Control Technology Key Laboratory (JCKYS2018207050)
摘要
摘要:海洋环境噪声和混响干扰严重、目标可分性差是主动声呐目标分类识别中的瓶颈问题。针对这一问题，该文基于主动声呐目标回波信号模型和分数阶傅里叶变换(FRFT)原理，推导了多阶次FRFT域特征表征形式，建立了FRFT域稀疏表示模型，提出了一种多阶次FRFT域特征融合的主动声呐目标稀疏表示分类方法。该方法通过FRFT的能量聚集性和稀疏分解的残差去除过程，达到了抑制噪声和混响干扰的目的；通过多阶次FRFT域特征的融合，增加目标之间的可分性，进而实现海洋环境中低信混比条件下的主动声呐目标分类。实验结果表明，所提方法在信混比达到0 dB的条件下，分类准确率能够达到90%以上。
关键词:主动声呐/
分数阶傅里叶变换/
特征融合/
稀疏表示/
目标分类
Abstract:Marine environment noise and reverberation interference are serious, and the poor target separability is the bottleneck problem in active sonar target classification and recognition. In order to solve this problem, based on the echo signal model of active sonar target and the principle of FRactional Fourier Transform (FRFT), this paper deduces the multi-order FRFT domain feature representation form, establishes the FRFT domain sparse representation model, and proposes a method to classify the sparse representation of active sonar targets with multi-order FRFT domain feature fusion. The method achieves the purpose of suppressing noise and reverberation interference through the energy aggregation of FRFT and removing the residual of sparse decomposition; Through the fusion of multi-order FRFT domain features, the separability of targets is improved, and the active sonar target classification with low SNR is realized. Experimental results show that the classification accuracy of the proposed method can reach more than 90% when the SNR is about 0 dB.
Key words:Active sonar/
FRactional Fourier Transform (FRFT)/
Feature fusion/
Sparse representation/
Target classification
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=a9c0bede-989b-4073-a378-a649dab0bbd1
