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。
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.
作者
周光宇
刘邦权
张亶
ZHOU Guangyu;LIU Bangquan;ZHANG Dan(College of Digital Technology and Engineering, Ningbo University of Finance and Economics, Ningbo 315175, China;College of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China)
出处
《国土资源遥感》
CSCD
北大核心
2020年第2期33-39,共7页
Remote Sensing for Land & Resources
基金
浙江省自然科学项目“测地度量的快速估算及其应用”(编号:LY19F020001)资助。
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
synthetic aperture Radar
target recognition
variational mode decomposition
joint sparse representation