A Novel Two-Stage Learning-Based Phase Unwrapping Algorithm via Multimodel Fusion

Phase unwrapping (PhU) is one of the key steps in interferometric synthetic aperture radar (InSAR) data processing, and it is a considerable challenge for PhU in regions with high-noise and large-gradient changes. Deep learning phase unwrapping (DLPU) can better solve this problem. However, a single...

Full description

Saved in:
Bibliographic Details
Main Authors: Chao Yan, Tao Li, Yandong Gao, Shijin Li, Xiang Zhang, Xuefei Zhang, Di Zhang, Huiqin Liu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10884057/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330111714689024
author Chao Yan
Tao Li
Yandong Gao
Shijin Li
Xiang Zhang
Xuefei Zhang
Di Zhang
Huiqin Liu
author_facet Chao Yan
Tao Li
Yandong Gao
Shijin Li
Xiang Zhang
Xuefei Zhang
Di Zhang
Huiqin Liu
author_sort Chao Yan
collection DOAJ
description Phase unwrapping (PhU) is one of the key steps in interferometric synthetic aperture radar (InSAR) data processing, and it is a considerable challenge for PhU in regions with high-noise and large-gradient changes. Deep learning phase unwrapping (DLPU) can better solve this problem. However, a single DLPU algorithm still finds it difficult to obtain robust PhU results in regions with large-gradient changes. In addition, the performance of the same training model varies greatly for different data. To solve this problem, this paper combines a deep neural network model with the traditional PhU model and proposes a novel two-stage learning-based phase unwrapping (TLPU) algorithm via multimodel fusion. The major advantages of TLPU are as follows: 1) A high-resolution U-Net (HRU-Net) model trained on a dataset constructed according to InSAR interferometric geometry is utilized for the PhU for the first time, which effectively improves the performance of the DLPU. 2) TLPU utilizes the traditional PhU method to optimize the results of DLPU, addressing the issue of weak generalization ability of a single DLPU, while improving accuracy in areas with large-gradient changes. Experimental analysis was carried out using LT-1 data, and the results show that the proposed TLPU algorithm can achieve superior excellent results in large-gradient change regions compared with the commonly used PhU method, with root mean square errors of only 1.63 rad in experiment 1 and 1.96 rad in experiment 2.
format Article
id doaj-art-2a8382bbcb7e46c89c397199841d76fb
institution Kabale University
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-2a8382bbcb7e46c89c397199841d76fb2025-08-20T03:47:03ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01187468747910.1109/JSTARS.2025.354132210884057A Novel Two-Stage Learning-Based Phase Unwrapping Algorithm via Multimodel FusionChao Yan0https://orcid.org/0009-0004-4209-7880Tao Li1https://orcid.org/0000-0002-7676-7852Yandong Gao2https://orcid.org/0000-0002-6224-5711Shijin Li3https://orcid.org/0000-0001-9394-389XXiang Zhang4Xuefei Zhang5https://orcid.org/0000-0003-3352-3329Di Zhang6Huiqin Liu7Land Satellite Remote Sensing Application Center, Ministry of Natural Resources of the People&#x0027;s Republic of China, Beijing, ChinaLand Satellite Remote Sensing Application Center, Ministry of Natural Resources of the People&#x0027;s Republic of China, Beijing, ChinaSchool of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou, ChinaSchool of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou, ChinaLand Satellite Remote Sensing Application Center, Ministry of Natural Resources of the People&#x0027;s Republic of China, Beijing, ChinaLand Satellite Remote Sensing Application Center, Ministry of Natural Resources of the People&#x0027;s Republic of China, Beijing, ChinaSchool of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou, ChinaSchool of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou, ChinaPhase unwrapping (PhU) is one of the key steps in interferometric synthetic aperture radar (InSAR) data processing, and it is a considerable challenge for PhU in regions with high-noise and large-gradient changes. Deep learning phase unwrapping (DLPU) can better solve this problem. However, a single DLPU algorithm still finds it difficult to obtain robust PhU results in regions with large-gradient changes. In addition, the performance of the same training model varies greatly for different data. To solve this problem, this paper combines a deep neural network model with the traditional PhU model and proposes a novel two-stage learning-based phase unwrapping (TLPU) algorithm via multimodel fusion. The major advantages of TLPU are as follows: 1) A high-resolution U-Net (HRU-Net) model trained on a dataset constructed according to InSAR interferometric geometry is utilized for the PhU for the first time, which effectively improves the performance of the DLPU. 2) TLPU utilizes the traditional PhU method to optimize the results of DLPU, addressing the issue of weak generalization ability of a single DLPU, while improving accuracy in areas with large-gradient changes. Experimental analysis was carried out using LT-1 data, and the results show that the proposed TLPU algorithm can achieve superior excellent results in large-gradient change regions compared with the commonly used PhU method, with root mean square errors of only 1.63 rad in experiment 1 and 1.96 rad in experiment 2.https://ieeexplore.ieee.org/document/10884057/Deep learning (DL)interferometric synthetic aperture radar (INSAR)<named-content xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" content-type="math" xlink:type="simple"> <inline-formula> <tex-math notation="LaTeX">$L_{1}$</tex-math> </inline-formula> </named-content>-normphase unwrapping (PhU)
spellingShingle Chao Yan
Tao Li
Yandong Gao
Shijin Li
Xiang Zhang
Xuefei Zhang
Di Zhang
Huiqin Liu
A Novel Two-Stage Learning-Based Phase Unwrapping Algorithm via Multimodel Fusion
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Deep learning (DL)
interferometric synthetic aperture radar (INSAR)
<named-content xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" content-type="math" xlink:type="simple"> <inline-formula> <tex-math notation="LaTeX">$L_{1}$</tex-math> </inline-formula> </named-content>-norm
phase unwrapping (PhU)
title A Novel Two-Stage Learning-Based Phase Unwrapping Algorithm via Multimodel Fusion
title_full A Novel Two-Stage Learning-Based Phase Unwrapping Algorithm via Multimodel Fusion
title_fullStr A Novel Two-Stage Learning-Based Phase Unwrapping Algorithm via Multimodel Fusion
title_full_unstemmed A Novel Two-Stage Learning-Based Phase Unwrapping Algorithm via Multimodel Fusion
title_short A Novel Two-Stage Learning-Based Phase Unwrapping Algorithm via Multimodel Fusion
title_sort novel two stage learning based phase unwrapping algorithm via multimodel fusion
topic Deep learning (DL)
interferometric synthetic aperture radar (INSAR)
<named-content xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" content-type="math" xlink:type="simple"> <inline-formula> <tex-math notation="LaTeX">$L_{1}$</tex-math> </inline-formula> </named-content>-norm
phase unwrapping (PhU)
url https://ieeexplore.ieee.org/document/10884057/
work_keys_str_mv AT chaoyan anoveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT taoli anoveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT yandonggao anoveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT shijinli anoveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT xiangzhang anoveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT xuefeizhang anoveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT dizhang anoveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT huiqinliu anoveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT chaoyan noveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT taoli noveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT yandonggao noveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT shijinli noveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT xiangzhang noveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT xuefeizhang noveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT dizhang noveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion
AT huiqinliu noveltwostagelearningbasedphaseunwrappingalgorithmviamultimodelfusion