A Coherence-Guided InSAR Phase Unwrapping Method With Cycle-Consistent Adversarial Networks
Phase unwrapping (PU) is a critical processing step for obtaining information on land surface deformation from interferometric synthetic aperture radar (InSAR) images. Traditional PU methods take the phase continuity assumption as the precondition. However, in actual applications, there are many fac...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10361554/ |
| _version_ | 1797357962941956096 |
|---|---|
| author | Jingqin Mu Yuzhu Wang Sheng Zhan Guoqing Yao Kun Liu Yueqin Zhu Lizhe Wang |
| author_facet | Jingqin Mu Yuzhu Wang Sheng Zhan Guoqing Yao Kun Liu Yueqin Zhu Lizhe Wang |
| author_sort | Jingqin Mu |
| collection | DOAJ |
| description | Phase unwrapping (PU) is a critical processing step for obtaining information on land surface deformation from interferometric synthetic aperture radar (InSAR) images. Traditional PU methods take the phase continuity assumption as the precondition. However, in actual applications, there are many factors that can cause phase discontinuities, resulting in large errors in the PU results. With the fast development of deep learning, the data-driven deep learning methods for PU may help address this issue. Therefore, this study proposes a coherence-guided InSAR PU method with cycle-consistent adversarial networks. In this method, PU was considered a pixel-level regression problem from the interferogram to the unwrapped phase; cycle-consistent adversarial networks as one-step PU model were imported with the interferogram as the input and the unwrapped phase as the output. Except for adversarial loss and cycle consistency loss, based on the PU theory and the coherence of SAR images, the <inline-formula><tex-math notation="LaTeX">$\mathcal {L}_{1}$</tex-math></inline-formula> loss with the weight of the coherence coefficient was added to guide the training process of networks. In addition to the traditional mean square error index, the root mean square value of the phase loop closure was introduced to evaluate the quality of the generated unwrapped phase. The results show that the proposed method can not only achieve the accuracy of the traditional PU method in the region with good coherence but also obtain better unwrapping results in the region with poor coherence, where the traditional PU method is restricted. It is also superior to the existing PU method with a conditional adversarial network. |
| first_indexed | 2024-03-08T14:53:08Z |
| format | Article |
| id | doaj.art-2a2b1c7eed894367be007a17771ef071 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-03-08T14:53:08Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-2a2b1c7eed894367be007a17771ef0712024-01-11T00:01:32ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-01172690270410.1109/JSTARS.2023.334351710361554A Coherence-Guided InSAR Phase Unwrapping Method With Cycle-Consistent Adversarial NetworksJingqin Mu0https://orcid.org/0000-0001-8624-0387Yuzhu Wang1https://orcid.org/0000-0003-0449-2973Sheng Zhan2https://orcid.org/0009-0005-8731-6124Guoqing Yao3https://orcid.org/0000-0003-0449-2973Kun Liu4https://orcid.org/0009-0005-0212-9355Yueqin Zhu5https://orcid.org/0009-0009-4090-1624Lizhe Wang6https://orcid.org/0000-0003-2766-0845School of Information Engineering, China University of Geosciences, Beijing, ChinaSchool of Information Engineering, China University of Geosciences, Beijing, ChinaSchool of Mathematics and Computational Science, Tangshan Normal University, Tangshan, ChinaSchool of Information Engineering, China University of Geosciences, Beijing, China7th Institute of Geology and Mineral Exploration of Shandong Province, Linyi, ChinaNational Institute of Natural Hazards, Ministry of Emergency Management, Beijing, ChinaSchool of Computer Science, China University of Geosciences, Wuhan, ChinaPhase unwrapping (PU) is a critical processing step for obtaining information on land surface deformation from interferometric synthetic aperture radar (InSAR) images. Traditional PU methods take the phase continuity assumption as the precondition. However, in actual applications, there are many factors that can cause phase discontinuities, resulting in large errors in the PU results. With the fast development of deep learning, the data-driven deep learning methods for PU may help address this issue. Therefore, this study proposes a coherence-guided InSAR PU method with cycle-consistent adversarial networks. In this method, PU was considered a pixel-level regression problem from the interferogram to the unwrapped phase; cycle-consistent adversarial networks as one-step PU model were imported with the interferogram as the input and the unwrapped phase as the output. Except for adversarial loss and cycle consistency loss, based on the PU theory and the coherence of SAR images, the <inline-formula><tex-math notation="LaTeX">$\mathcal {L}_{1}$</tex-math></inline-formula> loss with the weight of the coherence coefficient was added to guide the training process of networks. In addition to the traditional mean square error index, the root mean square value of the phase loop closure was introduced to evaluate the quality of the generated unwrapped phase. The results show that the proposed method can not only achieve the accuracy of the traditional PU method in the region with good coherence but also obtain better unwrapping results in the region with poor coherence, where the traditional PU method is restricted. It is also superior to the existing PU method with a conditional adversarial network.https://ieeexplore.ieee.org/document/10361554/Coherencecycle consistencygenerative adversarial networksinterferometric synthetic aperture radar (InSAR)phase unwrapping (PU) |
| spellingShingle | Jingqin Mu Yuzhu Wang Sheng Zhan Guoqing Yao Kun Liu Yueqin Zhu Lizhe Wang A Coherence-Guided InSAR Phase Unwrapping Method With Cycle-Consistent Adversarial Networks IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Coherence cycle consistency generative adversarial networks interferometric synthetic aperture radar (InSAR) phase unwrapping (PU) |
| title | A Coherence-Guided InSAR Phase Unwrapping Method With Cycle-Consistent Adversarial Networks |
| title_full | A Coherence-Guided InSAR Phase Unwrapping Method With Cycle-Consistent Adversarial Networks |
| title_fullStr | A Coherence-Guided InSAR Phase Unwrapping Method With Cycle-Consistent Adversarial Networks |
| title_full_unstemmed | A Coherence-Guided InSAR Phase Unwrapping Method With Cycle-Consistent Adversarial Networks |
| title_short | A Coherence-Guided InSAR Phase Unwrapping Method With Cycle-Consistent Adversarial Networks |
| title_sort | coherence guided insar phase unwrapping method with cycle consistent adversarial networks |
| topic | Coherence cycle consistency generative adversarial networks interferometric synthetic aperture radar (InSAR) phase unwrapping (PU) |
| url | https://ieeexplore.ieee.org/document/10361554/ |
| work_keys_str_mv | AT jingqinmu acoherenceguidedinsarphaseunwrappingmethodwithcycleconsistentadversarialnetworks AT yuzhuwang acoherenceguidedinsarphaseunwrappingmethodwithcycleconsistentadversarialnetworks AT shengzhan acoherenceguidedinsarphaseunwrappingmethodwithcycleconsistentadversarialnetworks AT guoqingyao acoherenceguidedinsarphaseunwrappingmethodwithcycleconsistentadversarialnetworks AT kunliu acoherenceguidedinsarphaseunwrappingmethodwithcycleconsistentadversarialnetworks AT yueqinzhu acoherenceguidedinsarphaseunwrappingmethodwithcycleconsistentadversarialnetworks AT lizhewang acoherenceguidedinsarphaseunwrappingmethodwithcycleconsistentadversarialnetworks AT jingqinmu coherenceguidedinsarphaseunwrappingmethodwithcycleconsistentadversarialnetworks AT yuzhuwang coherenceguidedinsarphaseunwrappingmethodwithcycleconsistentadversarialnetworks AT shengzhan coherenceguidedinsarphaseunwrappingmethodwithcycleconsistentadversarialnetworks AT guoqingyao coherenceguidedinsarphaseunwrappingmethodwithcycleconsistentadversarialnetworks AT kunliu coherenceguidedinsarphaseunwrappingmethodwithcycleconsistentadversarialnetworks AT yueqinzhu coherenceguidedinsarphaseunwrappingmethodwithcycleconsistentadversarialnetworks AT lizhewang coherenceguidedinsarphaseunwrappingmethodwithcycleconsistentadversarialnetworks |