基于核空间联合稀疏表示和指数平滑的多基地水下小目标识别

王佳维; 许枫; 杨娟

doi:10.12263/DZXB.20220603

您当前的位置：

首页 >

文章列表页 >

基于核空间联合稀疏表示和指数平滑的多基地水下小目标识别

学术论文 | 更新时间：2026-04-10

- 基于核空间联合稀疏表示和指数平滑的多基地水下小目标识别
- Multi-Static Underwater Small Target Recognition Based on Kernel Joint Sparse Representation and Exponential Smoothing
- 电子学报 2024年52卷第1期页码：217-231
- 作者机构：
  
  1.中国科学院声学研究所，北京 100190
  2.中国科学院大学，北京 100049
- 作者简介：
  
  [ "王佳维女，1995年生，河北廊坊人.中国科学院大学声学研究所博士研究生.主要研究方向为水声信号处理. E-mail: wangjiawei@mail.ioa.ac.cn" ]
  [ "杨娟女，1981年生，山西太原人.中国科学院大学声学研究所研究员.主要研究方向为高频声呐、水下小目标探测及声学智能信号处理等. E-mail: yangjuan@mail.ioa.ac.cn" ]
- 基金信息：
  
  国家重点研发计划(2018YFC0824103)
- DOI：10.12263/DZXB.20220603
  中图分类号： TB566;O427;P733.2;TP212
- 收稿：2022-05-25，
  
  修回：2022-09-26，
  
  纸质出版：2024-01-25
- 稿件说明：
移动端阅览
王佳维,许枫,杨娟.基于核空间联合稀疏表示和指数平滑的多基地水下小目标识别[J].电子学报,2024,52(01):217-231.

WANG Jia-wei,XU Feng,YANG Juan.Multi-Static Underwater Small Target Recognition Based on Kernel Joint Sparse Representation and Exponential Smoothing[J].ACTA ELECTRONICA SINICA,2024,52(01):217-231.
王佳维,许枫,杨娟.基于核空间联合稀疏表示和指数平滑的多基地水下小目标识别[J].电子学报,2024,52(01):217-231. DOI： 10.12263/DZXB.20220603.

WANG Jia-wei,XU Feng,YANG Juan.Multi-Static Underwater Small Target Recognition Based on Kernel Joint Sparse Representation and Exponential Smoothing[J].ACTA ELECTRONICA SINICA,2024,52(01):217-231. DOI： 10.12263/DZXB.20220603.

摘要

针对多基地水下小目标分类识别问题，本文提出了一种基于核空间联合稀疏表示和指数平滑的多基地水下小目标识别方法.对水下目标多角度散射信号提取6种典型的具有信息互补性和关联性的特征，提出一种随机森林（Random Forest，RF）和最小冗余最大相关（minimum Redundancy and Maximum Relevance，mRMR）相结合的特征选择方法（RF-mRMR），得出综合的特征重要性排序结果.通过实验得出分类模型所需的最优特征子集，达到降低数据处理复杂度和提高目标分类结果的目的.为了捕捉到数据中的高阶结构，在联合稀疏表示模型的基础上，使用核函数将线性不可分的特征数据映射到高维核特征空间.为了充分挖掘稀疏重构后包含在残差波段中的有用信息，使用指数平滑公式对具有一定意义的残差信息进行再利用，最后由核特征空间下的最小误差准则判定目标的类别.应用本文提出的方法对4类目标的海试数据进行识别，结果表明，相较于其他7种对比算法，本文提出的改进方法具有更好的分类性能，而且大多数情况下，本文提出的算法在双基地声呐模式下具有比单基地声呐更高的识别准确率和更低的虚警率.

Abstract

Aiming at the problem of multi-static underwater small target classification and recognition

a multi-static underwater small target recognition method based on joint sparse representation of kernel space and exponential smoothing is proposed. Six typical features with information complementarity and correlation are extracted from the multi angle scattering signals of underwater targets. A feature selection method (RF-mRMR) combining random forest (RF) and minimum redundancy maximum correlation (mRMR) is proposed to obtain the comprehensive feature importance ranking results. The optimal feature subset required by the classification model is obtained through experiments

so as to reduce the complexity of data processing and improve the result of target classification. In order to capture the high-order structure in the data

based on the joint sparse representation model

the kernel function is used to map the linearly indivisible feature data to the high-dimensional kernel feature space. In order to fully mine the useful information contained in the residual band after sparse reconstruction

the exponential smoothing formula is used to reuse the residual information with certain significance. Finally

the category of the target is determined by the minimum error criterion under the kernel feature space. The method proposed in this paper is applied to identify the sea trial data of four types of targets. The results show that the improved method has better classification performance than the other seven comparison algorithms in this paper. In most cases

the proposed algorithm has higher recognition accuracy and lower false alarm rate than mono-static sonar in bistatic sonar mode.

关键词

Keywords

references

温涛 , 许枫 , 王梦宾 , 等 . 预测特征误差映射及其在多基地水下目标识别中的应用 [J]. 声学学报 , 2019 , 44 ( 1 ): 57 - 67 .

WEN T , XU F , WANG M B , et al . Predicted feature error mapping and its application in multi-static underwater target recognition [J]. Acta Acustica , 2019 , 44 ( 1 ): 57 - 67 . (in Chinese)

AI X , LI Y , WANG X , et al . Some results on characteristics of bistatic high-range resolution profiles for target classification [J]. IET Radar Sonar & Navigation , 2012 , 6 ( 5 ): 379 .

DOBECK G J . Fusing sonar images for mine detection and classification [C]// Proceedings SPIE 3710, Detection and Remediation Technologies for Mines and Minelike Targets IV . Orlando : SPIE , 1999 : 602 - 614 .

REED S , PETILLOT Y , BELL J . Automated approach to classification of mine-like objects in sidescan sonar using highlight and shadow information [J]. IEE Proceedings - Radar, Sonar and Navigation , 2004 , 151 ( 1 ): 48 .

严科伟 , 马爱民 . 基于神经网络的舰船目标识别研究 [J]. 指挥控制与仿真 , 2006 , 28 ( 1 ): 44 - 47 .

YAN K W , MA A M . Researches for ship identification based on neural network [J]. Command Control & Simulation , 2006 , 28 ( 1 ): 44 - 47 . (in Chinese)

HUAN R H , WANG C , PAN Y , et al . New structure for multi-aspect SAR image target recognition with multi-level joint consideration [J]. Multimedia Tools and Applications , 2016 , 75 ( 13 ): 7519 - 7540 .

XU L Y , CAO Z J . Sub-dictionary based joint sparse representation for multi-aspect SAR automatic target recognition [C]// The Proceedings of the Third International Conference on Communications, Signal Processing, and Systems . Cham : Springer , 2015 : 167 - 175 .

NGUYEN N H , NASRABADI N M , TRAN T D . Robust multi-sensor classification via joint sparse representation [C]// 14th International Conference on Information Fusion . Piscataway : IEEE , 2011 : 1 - 8 .

赵自璐 , 王世练 , 张炜 , 等 . 水下冲激噪声环境下基于多特征融合的信号调制方式识别 [J]. 厦门大学学报(自然科学版) , 2017 , 56 ( 3 ): 416 - 422 .

ZHAO Z L , WANG S L , ZHANG W , et al . Classification of signal modulation types based on multi-features fusion in impulse noise underwater [J]. Journal of Xiamen University (Natural Science) , 2017 , 56 ( 3 ): 416 - 422 . (in Chinese)

胡欣 , 吴晓红 , 雷翔 , 等 . 基于联合多特征字典稀疏表示的步态识别算法 [J]. 计算机科学与应用 , 2017 , 7 ( 4 ): 398 - 406 .

HU X , WU X H , LEI X , et al . Gait recognition algorithm based on sparse representation of joint multi-feature dictionary [J]. Computer Science and Application , 2017 , 7 ( 4 ): 398 - 406 . (in Chinese)

DAO M , TRAN-LUU T D , NASRABADI N M . Sparsity-based fusion of multiple sensors and multiple features for acoustic transients classification [C]// 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP) . Piscataway : IEEE , 2017 : 182 - 186 .

侯平魁 , 史习智 , 林良骥 , 等 . 水下目标识别的特征融合分类器设计 [J]. 电子学报 , 2001 , 29 ( 4 ): 443 - 446 .

HOU P K , SHI X Z , LIN L J , et al . Design of feature fusion classifier for underwater targets recognition [J]. Acta Electronica Sinica , 2001 , 29 ( 4 ): 443 - 446 . (in Chinese)

温涛 , 许枫 , 杨娟 , 等 . 连续隐马尔科夫模型在多基地目标识别中的应用 [J]. 应用声学 , 2017 , 36 ( 6 ): 512 - 520 .

WEN T , XU F , YANG J , et al . Multi-static underwater target recognition method based on continuous hidden Markov model [J]. Journal of Applied Acoustics , 2017 , 36 ( 6 ): 512 - 520 . (in Chinese)

PEI J F , HUANG Y L , HUO W B , et al . SAR automatic target recognition based on multiview deep learning framework [J]. IEEE Transactions on Geoscience and Remote Sensing , 2018 , 56 ( 4 ): 2196 - 2210 .

PEI J F , WANG Z Y , SUN X P , et al . FEF-Net: A deep learning approach to multiview SAR image target recognition [J]. Remote Sensing , 2021 , 13 ( 17 ): 3493 .

刘渭滨 , 邹智元 , 邢薇薇 . 模式分类中的特征融合方法 [J]. 北京邮电大学学报 , 2017 , 40 ( 4 ): 1 - 8 .

LIU W B , ZOU Z Y , XING W W . Feature fusion methods in pattern classification [J]. Journal of Beijing University of Posts and Telecommunications , 2017 , 40 ( 4 ): 1 - 8 . (in Chinese)

陈宏 . 结合多视角-多特征的SAR图像目标识别方法 [J]. 电子测量与仪器学报 , 2019 , 33 ( 9 ): 87 - 92 .

CHEN H . Target recognition method of SAR images by combination of multiple views and features [J]. Journal of Electronic Measurement and Instrumentation , 2019 , 33 ( 9 ): 87 - 92 . (in Chinese)

DAO M , NGUYEN N H , NASRABADI N M , et al . Collaborative multi-sensor classification via sparsity-based representation [J]. IEEE Transactions on Signal Processing , 2016 , 64 ( 9 ): 2400 - 2415 .

ZHANG H C , NASRABADI N M , HUANG T S , et al . Transient acoustic signal classification using joint sparse representation [C]// 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . Piscataway : IEEE , 2011 : 2220 - 2223 .

ZHANG H C , NASRABADI N M , ZHANG Y N , et al . Multi-view automatic target recognition using joint sparse representation [J]. IEEE Transactions on Aerospace and Electronic Systems , 2012 , 48 ( 3 ): 2481 - 2497 .

LAN X Y , MA A J , YUEN P C , et al . Joint sparse representation and robust feature-level fusion for multi-cue visual tracking [J]. IEEE Transactions on Image Processing , 2015 , 24 ( 12 ): 5826 - 5841 .

CHEN Y , NASRABADI N M , TRAN T D . Kernel sparse representation for hyperspectral target detection [C]// 2012 IEEE International Geoscience and Remote Sensing Symposium . Piscataway : IEEE , 2012 : 7484 - 7487 .

CHANDRAN V , ELGAR S , NGUYEN A . Detection of mines in acoustic images using higher order spectral features [J]. IEEE Journal of Oceanic Engineering , 2002 , 27 ( 3 ): 610 - 618 .

WEN T , XU F , YANG J , et al . An identification method based on multi-aspect target scattering characteristics [C]// 2016 IEEE/OES China Ocean Acoustics (COA) . Piscataway : IEEE , 2016 : 1 - 4 .

温福喜 , 刘宏伟 . 基于中心矩特征的空间目标识别方法 [J]. 雷达科学与技术 , 2007 , 5 ( 1 ): 8 - 12 .

WEN F X , LIU H W . Space target recognition based on central moment feature [J]. Radar Science and Technology , 2007 , 5 ( 1 ): 8 - 12 . (in Chinese)

孙长印 , 保铮 . 一种稳健的雷达成像超分辨算法 [J]. 电子科学学刊 , 2000 , 22 ( 5 ): 735 - 740 .

SUN C Y , BAO Z . A robust super resolution algorithm for radar imaging [J]. Journal of Electronics and Information Technology , 2000 , 22 ( 5 ): 735 - 740 . (in Chinese)

孙滨 . 水底掩埋物识别方法研究 [D]. 南京 : 东南大学 , 2006 .

金磊磊 , 梁红 , 陆禹 . 水下不同材料的回波特征提取与分类研究 [C]// 2016中国西部声学学术交流会论文集 . 上海 : 《声学技术》编辑部 , 2016 : 115 - 118 .

JIN L L , LIANG H , LU Y . Echo feature extraction and classification of different underwater materials [C]// Proceedings of 2016 Western China acoustic Symposium . Shanghai : Editorial Office of Technical Acoustics , 2016 : 115 - 118 . (in Chinese)

WANG J W , XU F , YANG J . An identification method of underwater targets based on sparse representation [C]// 2021 OES China Ocean Acoustics (COA) . Piscataway : IEEE , 2021 : 971 - 975 .

谢磊 . 基于HHT的水雷目标特征提取技术研究 [D]. 哈尔滨 : 哈尔滨工程大学 , 2008 .

XIE L . The Research on the Extraction of Mine based on the HHT [D]. Harbin : Harbin Engineering University , 2008 . (in Chinese)

李秀坤 , 谢磊 , 秦宇 . 应用希尔伯特黄变换的水下目标特征提取 [J]. 哈尔滨工程大学学报 , 2009 , 30 ( 5 ): 542 - 546 .

LI X K , XIE L , QIN Y . Underwater target feature extraction using Hilbert-Huang transform [J]. Journal of Harbin Engineering University , 2009 , 30 ( 5 ): 542 - 546 . (in Chinese)

HUANG N E , SHEN Z , LONG S R , et al . The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J]. Proceedings of the Royal Society of London Series A: Mathematical, Physical and Engineering Sciences , 1998 , 454 ( 1971 ): 903 - 995 .

赖祥源 , 朱勤东 , 陈火荣 , 等 . 基于RF特征选择和XGBoost模型的赤潮等级预测 [J]. 渔业研究 , 2021 , 43 ( 1 ): 1 - 12 .

LAI X Y , ZHU Q D , CHEN H R , et al . Red tide level prediction based on RF feature selection and XGBoost model [J]. Journal of Fisheries Research , 2021 , 43 ( 1 ): 1 - 12 . (in Chinese)

马国娟 , 吴辰文 , 刘文祎 . 基因数据集混合特征选择算法研究 [J]. 测控技术 , 2019 , 38 ( 10 ): 71 - 75 .

MA G J , WU C W , LIU W Y . Research on hybrid feature selection algorithm for gene data sets [J]. Measurement & Control Technology , 2019 , 38 ( 10 ): 71 - 75 . (in Chinese)

ZHANG L , ZHOU W D , CHANG P C , et al . Kernel sparse representation-based classifier [J]. IEEE Transactions on Signal Processing , 2012 , 60 ( 4 ): 1684 - 1695 .

CHEN F , YU W X , LIU X Z , et al . Combinational matching method of amplitude-scale and time-shift for radar HRRP recognition [C]// 2011 IEEE International Geoscience and Remote Sensing Symposium . Piscataway : IEEE , 2011 : 1311 - 1314 .

孙同晶 , 贺锦鹏 , 谷雨 . 基于稀疏分解的水下目标回波信号处理方法 [J]. 数据采集与处理 , 2016 , 31 ( 2 ): 282 - 288 .

SUN T J , HE J P , GU Y . Underwater echo signal processing method based on sparse decomposition [J]. Journal of Data Acquisition and Processing , 2016 , 31 ( 2 ): 282 - 288 . (in Chinese)

陈渤 , 刘宏伟 , 保铮 . 基于三种不同绝对对齐方法的分类器分析 [J]. 现代雷达 , 2006 , 28 ( 3 ): 58 - 62 .

CHEN B , LIU H W , BAO Z . Analysis of three kinds of classification based on different absolute alignment methods [J]. Modern Radar , 2006 , 28 ( 3 ): 58 - 62 . (in Chinese)

汤渭霖 . 声呐目标回波的亮点模型 [J]. 声学学报 , 1994 , 19 ( 2 ): 92 - 100 .

TANG W L . Highlight model of echoes from sonar targets [J]. Acta Acustica , 1994 , 19 ( 2 ): 92 - 100 . (in Chinese)

宁波 , 王运 , 邵鹏 , 等 . 基于包裹式框架的风功率特征选择与预测方法 [J]. 信息技术 , 2020 , 44 ( 12 ): 17 - 21 .

NING B , WANG Y , SHAO P , et al . Wind power feature selection and prediction method based on wrapped framework [J]. Information Technology , 2020 , 44 ( 12 ): 17 - 21 . (in Chinese)

COVER T , HART P . Nearest neighbor pattern classification [J]. IEEE Transactions on Information Theory , 1967 , 13 ( 1 ): 21 - 27 .

CORTES C , VAPNIK V . Support-vector networks [J]. Machine Learning , 1995 , 20 ( 3 ): 273 - 297 .

程锦盛 , 杜选民 , 曾赛 . 采用深度学习方法的水下目标听觉特征提取与识别技术研究 [C]// 2018年全国声学大会论文集 . 北京 : 中国声学学会 , 2018 : 167 - 168 .

CHENG J S , DU X , M , ZENG S . Research on extraction and recognition technique to auditory features of underwater target based on deep learning [C]// Proceedings of 2018 National Acoustic Conference . Beijing : The Acoustical Society of China , 2018 : 167 - 168 . (in Chinese)

龚健 , 陈耀霖 , 张志 . 基于多分类Logistic回归模型的区域土地利用变化及驱动因素研究 [J]. 湖北农业科学 , 2016 , 55 ( 17 ): 4545 - 4550 .

GONG J , CHEN Y L , ZHANG Z . Regional land use change and its driving forces analysis based on multinomial logistic regression [J]. Hubei Agricultural Sciences , 2016 , 55 ( 17 ): 4545 - 4550 . (in Chinese)

DIMITRIADIS G , NETO J P , KAMPFF A R . T-SNE visualization of large-scale neural recordings [J]. Neural Computation , 2018 , 30 ( 7 ): 1750 - 1774 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

带特征选择的综合因果多目标反事实解释方法

基于双模糊学习的鲁棒无监督特征选择算法

基于高阶矩特征选择和权值优化的信噪比估计

基于冗余覆盖信息约简的软件缺陷定位方法

基于混合进化算法的特征选择方法研究