A Novel Quality-Guided Two-Dimensional InSAR Phase Unwrapping Method via GAUNet
Phase unwrapping (PU) has always been a critical and challenging step in interferometric synthetic aperture radar (InSAR) data processing. Inspired by existing research, i.e., the PGNet, we propose a novel quality-guided 2-D InSAR PU method via deep learning, and regard PU as a two-stage process. In...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9496097/ |
id |
doaj-e9cd7fbd987c45479c2ffd2e250e3c21 |
---|---|
record_format |
Article |
spelling |
doaj-e9cd7fbd987c45479c2ffd2e250e3c212021-08-26T23:00:09ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01147840785610.1109/JSTARS.2021.30994859496097A Novel Quality-Guided Two-Dimensional InSAR Phase Unwrapping Method via GAUNetHai Wang0https://orcid.org/0000-0001-6206-8607Jun Hu1https://orcid.org/0000-0002-5412-2703Haiqiang Fu2https://orcid.org/0000-0003-2306-8721Changcheng Wang3https://orcid.org/0000-0003-4461-068XZhenhai Wang4School of Geosciences and Info-Physics, Central South University, Changsha, ChinaSchool of Geosciences and Info-Physics, Central South University, Changsha, ChinaSchool of Geosciences and Info-Physics, Central South University, Changsha, ChinaSchool of Geosciences and Info-Physics, Central South University, Changsha, ChinaSchool of Geosciences and Info-Physics, Central South University, Changsha, ChinaPhase unwrapping (PU) has always been a critical and challenging step in interferometric synthetic aperture radar (InSAR) data processing. Inspired by existing research, i.e., the PGNet, we propose a novel quality-guided 2-D InSAR PU method via deep learning, and regard PU as a two-stage process. In the first stage, the ambiguity gradient is estimated using the proposed global attention U-Net (GAUNet) architecture, which combines the classic U-Net structure and global attention mechanism. Then, in the second stage, the classical PU framework (e.g., the L1- or L2-norm) is applied as a post-processing operation to retrieve the absolute phase. Since class imbalance is a key factor affecting the estimation of ambiguity gradient, different strategies based on four commonly used quality maps are adopted to deal with the problem. The quality map is not only input as additional information for the guidance of the training process, but also participates in the construction of loss function. As a result, GAUNet can pay more attention to the nonzero ambiguity gradients. By using the number of residues as the evaluation metric, we can choose the optimum strategy for the restoration of the absolute phase. In addition to the simulated interferograms, the proposed method is tested both on a real topographic interferogram exhibiting rugged topography and phase aliasing and a differential interferogram measuring the deformation from MW 6.9 Hawaii earthquake, all yield state-of-art performance when comparing with the widely used traditional 2-D PU methods.https://ieeexplore.ieee.org/document/9496097/2-D phase unwrapping (2-D PU)ambiguity gradientclass imbalancedeep learning (DL)interferometric synthetic aperture radar (InSAR)quality-guided |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hai Wang Jun Hu Haiqiang Fu Changcheng Wang Zhenhai Wang |
spellingShingle |
Hai Wang Jun Hu Haiqiang Fu Changcheng Wang Zhenhai Wang A Novel Quality-Guided Two-Dimensional InSAR Phase Unwrapping Method via GAUNet IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2-D phase unwrapping (2-D PU) ambiguity gradient class imbalance deep learning (DL) interferometric synthetic aperture radar (InSAR) quality-guided |
author_facet |
Hai Wang Jun Hu Haiqiang Fu Changcheng Wang Zhenhai Wang |
author_sort |
Hai Wang |
title |
A Novel Quality-Guided Two-Dimensional InSAR Phase Unwrapping Method via GAUNet |
title_short |
A Novel Quality-Guided Two-Dimensional InSAR Phase Unwrapping Method via GAUNet |
title_full |
A Novel Quality-Guided Two-Dimensional InSAR Phase Unwrapping Method via GAUNet |
title_fullStr |
A Novel Quality-Guided Two-Dimensional InSAR Phase Unwrapping Method via GAUNet |
title_full_unstemmed |
A Novel Quality-Guided Two-Dimensional InSAR Phase Unwrapping Method via GAUNet |
title_sort |
novel quality-guided two-dimensional insar phase unwrapping method via gaunet |
publisher |
IEEE |
series |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
issn |
2151-1535 |
publishDate |
2021-01-01 |
description |
Phase unwrapping (PU) has always been a critical and challenging step in interferometric synthetic aperture radar (InSAR) data processing. Inspired by existing research, i.e., the PGNet, we propose a novel quality-guided 2-D InSAR PU method via deep learning, and regard PU as a two-stage process. In the first stage, the ambiguity gradient is estimated using the proposed global attention U-Net (GAUNet) architecture, which combines the classic U-Net structure and global attention mechanism. Then, in the second stage, the classical PU framework (e.g., the L1- or L2-norm) is applied as a post-processing operation to retrieve the absolute phase. Since class imbalance is a key factor affecting the estimation of ambiguity gradient, different strategies based on four commonly used quality maps are adopted to deal with the problem. The quality map is not only input as additional information for the guidance of the training process, but also participates in the construction of loss function. As a result, GAUNet can pay more attention to the nonzero ambiguity gradients. By using the number of residues as the evaluation metric, we can choose the optimum strategy for the restoration of the absolute phase. In addition to the simulated interferograms, the proposed method is tested both on a real topographic interferogram exhibiting rugged topography and phase aliasing and a differential interferogram measuring the deformation from MW 6.9 Hawaii earthquake, all yield state-of-art performance when comparing with the widely used traditional 2-D PU methods. |
topic |
2-D phase unwrapping (2-D PU) ambiguity gradient class imbalance deep learning (DL) interferometric synthetic aperture radar (InSAR) quality-guided |
url |
https://ieeexplore.ieee.org/document/9496097/ |
work_keys_str_mv |
AT haiwang anovelqualityguidedtwodimensionalinsarphaseunwrappingmethodviagaunet AT junhu anovelqualityguidedtwodimensionalinsarphaseunwrappingmethodviagaunet AT haiqiangfu anovelqualityguidedtwodimensionalinsarphaseunwrappingmethodviagaunet AT changchengwang anovelqualityguidedtwodimensionalinsarphaseunwrappingmethodviagaunet AT zhenhaiwang anovelqualityguidedtwodimensionalinsarphaseunwrappingmethodviagaunet AT haiwang novelqualityguidedtwodimensionalinsarphaseunwrappingmethodviagaunet AT junhu novelqualityguidedtwodimensionalinsarphaseunwrappingmethodviagaunet AT haiqiangfu novelqualityguidedtwodimensionalinsarphaseunwrappingmethodviagaunet AT changchengwang novelqualityguidedtwodimensionalinsarphaseunwrappingmethodviagaunet AT zhenhaiwang novelqualityguidedtwodimensionalinsarphaseunwrappingmethodviagaunet |
_version_ |
1721189198382235648 |