Please wait a minute...
 
国土资源遥感  2020, Vol. 32 Issue (2): 33-39    DOI: 10.6046/gtzyyg.2020.02.05
  技术方法 本期目录 | 过刊浏览 | 高级检索 |
基于变分模态分解的SAR图像目标识别方法
周光宇1, 刘邦权1, 张亶2
1.宁波财经学院数字技术与工程学院,宁波 315175
2.浙江大学计算机科学与技术学院,杭州 310058
Target recognition in SAR images based on variational mode decomposition
Guangyu ZHOU1, Bangquan LIU1, Dan ZHANG2
1. College of Digital Technology and Engineering, Ningbo University of Finance and Economics, Ningbo 315175, China
2. College of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China
全文: PDF(1752 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

为提升合成孔径雷达(synthetic aperture Radar,SAR)目标识别性能,提出基于变分模态分解算法(variational mode decomposition,VMD)的SAR图像目标识别方法。首先采用二维变分模态分解算法(bidimensional VMD,BVMD)对SAR图像进行分解,从而获得多模态的表示; 然后采用联合稀疏表示对SAR图像的多模态特征进行同时表征; 最后基于最小重构误差的原则判定目标类别。在MSTAR数据集上对提出方法进行性能测试,结果显示,在标准操作条件(standard operating condition,SOC)下对10类目标的识别率达到99.24%,在型号差异、俯仰角差异、噪声干扰条件下的性能也优于现有几类方法,证实了方法的有效性。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
周光宇
刘邦权
张亶
关键词 合成孔径雷达目标识别变分模态分解联合稀疏表示    
Abstract

In order to improve synthetic aperture Radar (SAR) target recognition performance, the authors propose a method based on variational mode decomposition (VMD). First, the bidimensional VMD (BVMD) is employed to decompose SAR images, thus obtaining multi-mode representations. Afterwards, the joint sparse representation is employed to represent the multiple modes. Finally, the target label is determined based on the minimum reconstruction error. The proposed method was tested on the MSTAR dataset. It could achieve a recognition rate of 99.24% on 10 classes of targets under the standard operating condition (SOC). In addition, its performance outperforms some other SAR target recognition methods under configuration variance, depression angle variance, and noise corruption. The results have confirmed the validity of the proposed method.

Key wordssynthetic aperture Radar    target recognition    variational mode decomposition    joint sparse representation
收稿日期: 2019-06-14      出版日期: 2020-06-18
:  TP753  
基金资助:浙江省自然科学项目“测地度量的快速估算及其应用”(LY19F020001)
作者简介: 周光宇(1963-),男,硕士,副教授,研究方向为嵌入式系统,图像处理,传感网络。Email: happyday_zh@163.com。
引用本文:   
周光宇, 刘邦权, 张亶. 基于变分模态分解的SAR图像目标识别方法[J]. 国土资源遥感, 2020, 32(2): 33-39.
Guangyu ZHOU, Bangquan LIU, Dan ZHANG. Target recognition in SAR images based on variational mode decomposition. Remote Sensing for Land & Resources, 2020, 32(2): 33-39.
链接本文:  
https://www.gtzyyg.com/CN/10.6046/gtzyyg.2020.02.05      或      https://www.gtzyyg.com/CN/Y2020/V32/I2/33
Fig.1  基于变分模态分解的SAR目标识别方法流程
Fig.2  10类目标的光学图像
类别 训练集图像数量/幅 测试集图像数量/幅
BMP2 233 195
BTR70 233 196
T72 232 196
T62 299 273
BRDM2 298 274
BTR60 256 195
ZSU23/4 299 274
D7 299 274
ZIL131 299 274
2S1 299 274
Tab.1  SOC条件实验设置
类别 BMP2 BTR70 T72 T62 BDRM2 BTR60 ZSU23/4 D7 ZIL131 2S1
BMP2 0.985 0 0.005 0.010 0 0 0 0 0 0
BTR70 0 1.000 0 0 0 0 0 0 0 0
T72 0 0 0.985 0 0.005 0 0.005 0 0 0.005
T62 0 0.004 0 0.989 0 0 0 0 0 0.007
BDRM2 0 0 0 0 0.996 0 0 0 0.004 0
BTR60 0 0 0 0.010 0 0.990 0 0 0 0
ZSU23/4 0 0 0 0 0 0 0.993 0 0 0.007
D7 0.004 0.004 0 0 0.007 0 0 0.985 0 0
ZIL131 0 0 0 0 0 0 0 0 1.0 0
2S1 0.004 0 0 0 0 0 0 0 0.003 0.993
Tab.2  SOC条件下本文方法的混淆矩阵
方法类型 平均识别率/% 平均时间消耗/ms
本文方法 99.24 75.4
SVM 96.94 69.5
SRC 97.26 62.7
CNN 99.08 78.6
单演信号法 99.10 80.1
Tab.3  SOC条件下平均识别率和平均时间消耗
类别 训练集图像数量/幅 测试集图像数量/幅
BMP2 233(Sn_9563) 196(Sn_9566)
196(Sn_c21)
BTR70 233(Sn_c71) 196(Sn_c71)
T72 232(Sn_132) 195(Sn_812)
191(Sn_s7)
Tab.4  型号差异下实验设置
方法类型 平均识别率/%
本文方法 97.82
SVM 94.58
SRC 95.72
CNN 96.07
单演信号法 97.14
Tab.5  型号差异下平均识别率
类型 俯仰角 2S1 BDRM2 ZSU23/4
训练集图像
数量/幅
17° 299 298 299
测试集图像 30° 288 287 288
数量/幅 45° 303 303 303
Tab.6  俯仰角变化下实验设置
Fig.3  俯仰角变化条件下平均识别率
Fig.4  各类方法在噪声干扰下的性能
[1] El-Darymli K, Gill E W, McGuire P,et al.Automatic target recognition in synthetic aperture Radar imagery:A state-of-the-art review[J]. IEEE Access, 2016,4(1):6014-6058.
[2] 文贡坚, 朱国强, 殷红成, 等. 基于三维电磁散射参数化模型的SAR目标识别方法[J]. 雷达学报, 2017,6(2):115-135.
Wen G J, Zhu G Q, Yin H C, et al. SAR ATR based on 3D parametric electromagnetic scattering model[J]. Journal of Radar, 2017,6(2):115-135.
[3] Amoon M, Rezai-Rad G A.Automatic target recognition of synthetic aperture Radar(SAR) images based on optimal selection of Zernike moment features[J]. IET Computer Vision, 2014,8(2):77-85.
[4] Ding B Y, Wen G J, Ma C H, et al. Target recognition in synthetic aperture Radar images using binary morphological operations[J]. Journal of Applied Remote Sensing, 2016,10(4):046006.
[5] Park J, Park S, Kim Y, et al. New discrimination features for SAR automatic target recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2013,10(3):476-480.
[6] Anagnostopoulos G C. SVM-based target recognition from synthetic aperture Radar images using target region outline descriptors[J]. Nonlinear Analysis, 2009,71(2):2934-2939.
[7] 谢晴, 张洪. SAR图像多层次正则化增强及在目标识别中的应用[J]. 电子测量与仪器学报, 2018,32(9):157-162.
Xie Q, Zhang H. Multi-level SAR image enhancement based on regularization with application to target recognition[J]. Journal of Electronic Measurement and Instrumentation, 2018,32(9):157-162.
[8] Mishra, Amit K. Validation of PCA and LDA for SAR ATR [C]//IEEE TENCON.IEEE, 2008: 1-6.
[9] 韩萍, 王欢. 结合KPCA和稀疏表示的SAR目标识别方法研究[J]. 信号处理, 2013,29(13):1696-1701.
Han P, Wang H. Research on the synthetic aperture Radar target recognition based on KPCA and sparse representation[J]. Journal of Signal Processing, 2013,29(13):1696-1701.
[10] Cui Z Y, Cao Z J, Yang J Y, et al. Target recognition in synthetic aperture Radar via non-negative matrix factorization[J]. IET Radar, Sonar and Navigation, 2015,9(9):1376-1385.
[11] 李帅, 许悦雷, 马时平, 等. 基于小波变换和深层稀疏编码的SAR目标识别[J]. 电视技术, 2014,38(13):31-35.
Li S, Xu Y L, Ma S P, et al. SAR target recognition using wavelet transform and deep sparse autoencoders[J]. Video Engineering, 2014,38(13):31-35.
[12] Dong G G, Kuang G Y, Wang N, et al. SAR target recognition via joint sparse representation of monogenic signal[J]. IEEE Journal of Selected Topics Applied Earth Observation and Remote Sensing, 2015,8(7):3316-3328.
[13] 丁柏圆, 文贡坚, 余连生, 等. 属性散射中心匹配及其在SAR目标识别中的应用[J]. 雷达学报, 2017,6(2):157-166.
Ding B Y, Wen G J, Yu L S, et al. Matching of attributed scattering center and its application to synthetic aperture Radar automatic target recognition[J]. Journal of Radar, 2017,6(2):157-166.
[14] Ding B Y, Wen G J, Zhong J R, et al. A robust similarity measure for attributed scattering center sets with application to SAR ATR[J]. Neurocomputing, 2017,219:130-143.
doi: 10.1016/j.neucom.2016.09.007
[15] Tian S R, Yin K Y, Wang C, et al. A SAR ATR method based on scattering centre feature and bipartite graph matching[J]. IETE Technical Review, 2015,32(5):364-375.
[16] Liu H C, Li S T. Decision fusion of sparse representation and support vector machine for SAR image target recognition[J]. Neurocomputing 2013,113:97-104.
[17] Thiagaraianm J, Ramamurthy K, Knee P P, et al. Sparse representations for automatic target classification in SAR images [C]//4th Communications,Control and Signal Processing, 2010: 1-4.
[18] Chen S Z, Wang H P, Xu F, et al. Target classification using the deep convolutional networks for SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016,54(8):4806-4817.
[19] Ding J, Chen B, Liu H W, et al. Convolutional neural network with data augmentation for SAR target recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2016,13(3):1-5.
[20] Dragomiretskiy K, Zosso D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014,62(3):531-544.
[21] 陆振宇, 卢亚敏, 夏志巍, 等. 基于变分模态分解和小波分析的语音信号去噪方法[J]. 现代电子技术, 2018,41(13):47-51.
Lu Z Y, Lu Y M, Xia Z W, et al. Speech signal denoising based on VMD and wavelet analysis[J]. Modern Electronics Technique, 2018,41(13):47-51.
[22] 任刚, 贾继德, 梅检民, 等. 基于变分模态分级的和去趋势波动分析的柴油机振动信号去噪方法[J]. 内燃机工程, 2019,40(2):76-82.
Ren G, Jia J D, Mei J M, et al. Vibration signal denoising method of diesel engines based on VMD and DFA[J]. Chinese International Combustion Engine Engineering, 2019,40(2):76-82.
[23] 刘嘉敏, 彭玲, 袁佳成, 等. 基于二维变分模态分解和自适应中值滤波的图像去噪方法[J]. 计算机应用研究, 2017,34(10):3149-3152.
Liu J M, Peng L, Yuan J C, et al. Image denoising method based on bi-dimensional variational mode decomposition and adaptive median filtering[J]. Application Research of Computers, 2017,34(10):3149-3152.
[24] Zhang H C, Nasrabadi M N, Zhang Y N, et al. Multi-view automatic target recognition using joint sparse representation[J]. IEEE Transactions on Aerospace and Electronic System, 2012,48(3):2481-2497.
[25] Ji S H, Dunson D, Carin L. Multitask compressive sensing[J]. IEEE Transactions on Signal Processing, 2009,57(1), 92-106.
[1] 董天成, 杨肖, 李卉, 张志, 齐睿. 基于Faster R-CNN和MorphACWE模型的SAR图像高原湖泊提取[J]. 国土资源遥感, 2021, 33(1): 129-137.
[2] 江珊, 王春, 宋宏利, 刘玉锋. 基于SAR与光学遥感数据相结合的农作物种植类型识别研究[J]. 国土资源遥感, 2020, 32(4): 105-110.
[3] 白泽朝, 汪宝存, 靳国旺, 徐青, 张红敏, 刘辉. Sentinel-1A数据矿区地表形变监测适用性分析[J]. 国土资源遥感, 2019, 31(2): 210-217.
[4] 王念秦, 乔德京, 符喜优. 滤波参数对Goldstein干涉相位图滤波性能的影响分析[J]. 国土资源遥感, 2019, 31(1): 117-124.
[5] 郑鸿瑞, 徐志刚, 甘乐, 陈玲, 杨金中, 杜培军. 合成孔径雷达遥感地质应用综述[J]. 国土资源遥感, 2018, 30(2): 12-20.
[6] 金永涛, 杨秀峰, 高涛, 郭会敏, 刘世盟. 基于面向对象与深度学习的典型地物提取[J]. 国土资源遥感, 2018, 30(1): 22-29.
[7] 许斌. 基于非高斯分布的全极化SAR数据无监督分类[J]. 国土资源遥感, 2017, 29(2): 90-96.
[8] 刘斌, 葛大庆, 李曼, 张玲, 王艳, 郭小方, 张晓博. 地基合成孔径雷达干涉测量技术及其应用[J]. 国土资源遥感, 2017, 29(1): 1-6.
[9] 祁帅, 张永红, 汪慧琴. 林火干扰区全极化SAR影像的散射特性分析[J]. 国土资源遥感, 2016, 28(2): 48-53.
[10] 卞小林, 邵芸, 张风丽, 符喜优. 典型地物微波特性知识库的设计与实现[J]. 国土资源遥感, 2015, 27(4): 189-194.
[11] 刘惠颖, 郭华东, 张露. 基于HJ-1CSAR数据的辽东湾海冰分类[J]. 国土资源遥感, 2014, 26(3): 125-129.
[12] 张冬华, 张春华, 刘芮, 姜焱光. 基于Mini-RF雷达数据的月球水冰探测[J]. 国土资源遥感, 2014, 26(1): 110-114.
[13] 王晓华, 邓喀中, 杨化超. 集成互补不变特征的SAR影像自动配准[J]. 国土资源遥感, 2014, 26(1): 52-56.
[14] 侯云峰, 阳丰俊, 杨效余, 王玉璞. 基于形态学重构运算的地面目标识别算法[J]. 国土资源遥感, 2012, 24(3): 11-15.
[15] 巩彪, 黄韦艮, 陈鹏. 基于改进的归一化Hough变换的ASAR图像船只尾迹检测[J]. 国土资源遥感, 2012, 24(3): 33-37.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-2
版权所有 © 2015 《自然资源遥感》编辑部
地址:北京学院路31号中国国土资源航空物探遥感中心 邮编:100083
电话:010-62060291/62060292 E-mail:zrzyyg@163.com
本系统由北京玛格泰克科技发展有限公司设计开发