DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Phi-Net: Deep Residual Learning for InSAR Parameters Estimation

Sica, Francescopaolo and Gobbi, Giorgia and Rizzoli, Paola and Bruzzone, Lorenzo (2020) Phi-Net: Deep Residual Learning for InSAR Parameters Estimation. IEEE Transactions on Geoscience and Remote Sensing. IEEE - Institute of Electrical and Electronics Engineers. doi: 10.1109/TGRS.2020.3020427. ISSN 0196-2892.

[img] PDF - Published version


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 Phi-Net, for the joint estimation of the interferometric phase and coherence. Phi-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 Phi-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 Phi-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.

Item URL in elib:https://elib.dlr.de/140350/
Document Type:Article
Title:Phi-Net: Deep Residual Learning for InSAR Parameters Estimation
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Sica, FrancescopaoloUNSPECIFIEDhttps://orcid.org/0000-0003-1593-1492UNSPECIFIED
Rizzoli, PaolaUNSPECIFIEDhttps://orcid.org/0000-0001-9118-2732UNSPECIFIED
Bruzzone, LorenzoUniversity of TrentoUNSPECIFIEDUNSPECIFIED
Date:15 September 2020
Journal or Publication Title:IEEE Transactions on Geoscience and Remote Sensing
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:Yes
Publisher:IEEE - Institute of Electrical and Electronics Engineers
Keywords:Deep Learning, Residual Learning, SAR Interferometry, estimation
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - SAR methods
Location: Oberpfaffenhofen
Institutes and Institutions:Microwaves and Radar Institute
Deposited By: Sica, Dr. Francescopaolo
Deposited On:12 Jan 2021 17:47
Last Modified:15 Jul 2021 16:26

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.