摘要
为了提高合成孔径雷达(SAR)图像目标的识别性能,将多分辨率表示与复数域卷积神经网(CNN)联合使用。首先通过对原始SAR图像的时频域进行处理,获得其多分辨率表示图像;然后采用复数域CNN分别对原始SAR图像及其多分辨率表示图像进行分类;接着对分类结果进行线性加权融合,根据融合结果对测试样本类别进行判决;最后基于MSTAR数据集对所提方法在标准和扩展的操作条件下进行实验。实验结果表明,所提方法具有有效性及稳健性。
To improve the recognition performance of synthetic aperture radar(SAR)image targets,multi-resolution representation and a complex domain convolutional neural network(CNN)are used in combination.Initially,the original SAR image is processed in time and frequency domain to obtain its multi-resolution representation image.Then,the complex domain CNN is used to classify the original image and its multi-resolution representation image.The classification results are weighted using a linearly weighted fusion scheme,and the test sample classification is evaluated according to the fusion result.Finally,the proposed method is tested under standard and extended operating conditions based on the MSTAR data set.The experimental results show that the proposed method is both effective and robust.
作者
乔良才
Qiao Liangcai(School of Information Engineering(College of Big Data),Xuzhou University of Technology,Xuzhou,Jiangsu 221018,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2020年第24期90-98,共9页
Laser & Optoelectronics Progress
基金
江苏省现代教育技术研究2017年度课题(55518)。
关键词
图像处理
合成孔径雷达
目标识别
多分辨率表示
复数域CNN
线性加权融合
image processing
synthetic aperture radar
target identification
multi-resolution representation
complex domain CNN
linear weighting fusion