Inversion of Rough Surface Parameters From SAR Images Using Simulation-Trained Convolutional Neural Networks
Inversion of Rough Surface Parameters From SAR Images Using Simulation-Trained Convolutional Neural Networks
复制标题
使用模拟训练的卷积神经网络从 SAR 图像反演粗糙表面参数
DOI：
10.1109/lgrs.2018.2822821
复制
发表时间：
2018-07-01
影响因子：
4.8
通讯作者：
Liu, Qing Huo
中科院分区：
文献类型：
--
作者：
Song, Tao;Kuang, Lei;Liu, Qing Huo
本文研究了利用深度卷积神经网络（cnn）从微波图像中反演粗糙表面参数（均方根高度和相关长度）。采用计算电磁法对深度CNN的训练数据进行数值模拟。由于CNN具有强大的图像特征提取能力，首先将粗糙表面的散射场通过插值的快速傅里叶变换转换为微波图像，然后再输入到CNN中。为了减少过拟合，使用了正则化技术和dropout层。本文提出的CNN由5对卷积层和maxpooling层组成，另外还有两个用于特征提取的卷积层和两个用于参数回归的全连接层。实验结果证明了利用深度神经网络反演粗糙表面电磁散射参数的可行性。提出了CNN在微波遥感数据粗糙表面参数反演中的应用前景。
This letter investigates the inversion of rough surface parameters (the root mean square height and the correlation length) from microwave images by using deep convolutional neural networks (CNNs). Training data for the deep CNN are simulated numerically using computational electromagnetic method. As CNN is powerful in extracting image features, scattering field from rough surfaces is first converted to microwave images via interpolated fast Fourier transform and then fed into the CNN. In order to reduce overfitting, the regularization technique and dropout layer are used. The proposed CNN consists of five pairs of convolutional and maxpooling layers and two additional convolution layers for feature extraction and two fully connected layers for parameter regression. The experimental results demonstrated the feasibility using deep neural networks for the parameter inversion of rough surface from electromagnetic scattering fields. It suggests potential application of CNN for rough surface parameter inversion from microwave sensing data.