Φ-Net: Deep Residual Learning for InSAR Parameters Estimation

Francescopaolo Sica; Giorgia Gobbi; Paola RizzoliLorenzo Bruzzone

首页> 外文期刊>IEEE Transactions on Geoscience and Remote Sensing >Φ-Net: Deep Residual Learning for InSAR Parameters Estimation

【24h】

Φ-Net: Deep Residual Learning for InSAR Parameters Estimation

机译：Φ-Net: Deep Residual Learning for InSAR Parameters Estimation

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

Nowadays, deep learning (DL) finds application in a large number of scientific fields, among which the estimation and the enhancement of signals disrupted by the noise of different natures. In this article, we address the problem of the estimation of the interferometric parameters from synthetic aperture radar (SAR) data. In particular, we combine convolutional neural networks together with the concept of residual learning to define a novel architecture, named &inline-formula& &tex-math notation="LaTeX"&$Phi $ &/tex-math&&/inline-formula&-Net, for the joint estimation of the interferometric phase and coherence. &inline-formula& &tex-math notation="LaTeX"&$Phi $ &/tex-math&&/inline-formula&-Net is trained using synthetic data obtained by an innovative strategy based on the theoretical modeling of the physics behind the SAR acquisition principle. This strategy allows the network to generalize the estimation problem with respect to: 1) different noise levels; 2) the nature of the imaged target on the ground; and 3) the acquisition geometry. We then analyze the &inline-formula& &tex-math notation="LaTeX"&$Phi $ &/tex-math&&/inline-formula&-Net performance on an independent data set of synthesized interferometric data, as well as on real InSAR data from the TanDEM-X and Sentinel-1 missions. The proposed architecture provides better results with respect to state-of-the-art InSAR algorithms on both synthetic and real test data. Finally, we perform an application-oriented study on the retrieval of the topographic information, which shows that &inline-formula& &tex-math notation="LaTeX"&$Phi $ &/tex-math&&/inline-formula&-Net is a strong candidate for the generation of high-quality digital elevation models at a resolution close to the one of the original single-look complex data.

著录项

来源
《IEEE Transactions on Geoscience and Remote Sensing》 |2021年第5期|3917-3941|共25页
作者
Francescopaolo Sica; Giorgia Gobbi; Paola RizzoliLorenzo Bruzzone;
展开▼
作者单位

German Aerospace Center, Microwaves and Radar Institute, We?ling, Germany;

Department of Information Engineering and Computer Science, University of Trento, Trento, Italy;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类地球物理学;遥感技术;
关键词
Estimation; Synthetic aperture radar; Coherence; Noise reduction; Convolution; Measurement; Wavelet transforms; convolutional neural network (CNN); deep learning (DL); denoising; interferometric phase; residual learning; synthetic aperture radar (SAR) interferometry;

Φ-Net: Deep Residual Learning for InSAR Parameters Estimation

摘要

著录项

相关主题

期刊订阅