A Robust InSAR Phase Unwrapping Method via Phase Gradient Estimation Network
Phase unwrapping is a critical step in synthetic aperture radar interferometry (InSAR) data processing chains. In almost all phase unwrapping methods, estimating the phase gradient according to the phase continuity assumption (PGE-PCA) is an essential step. The phase continuity assumption is not alw...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/22/4564 |
| _version_ | 1797508577227702272 |
|---|---|
| author | Liming Pu Xiaoling Zhang Zenan Zhou Liang Li Liming Zhou Jun Shi Shunjun Wei |
| author_facet | Liming Pu Xiaoling Zhang Zenan Zhou Liang Li Liming Zhou Jun Shi Shunjun Wei |
| author_sort | Liming Pu |
| collection | DOAJ |
| description | Phase unwrapping is a critical step in synthetic aperture radar interferometry (InSAR) data processing chains. In almost all phase unwrapping methods, estimating the phase gradient according to the phase continuity assumption (PGE-PCA) is an essential step. The phase continuity assumption is not always satisfied due to the presence of noise and abrupt terrain changes; therefore, it is difficult to get the correct phase gradient. In this paper, we propose a robust least squares phase unwrapping method that works via a phase gradient estimation network based on the encoder–decoder architecture (PGENet) for InSAR. In this method, from a large number of wrapped phase images with topography features and different levels of noise, the deep convolutional neural network can learn global phase features and the phase gradient between adjacent pixels, so a more accurate and robust phase gradient can be predicted than that obtained by PGE-PCA. To get the phase unwrapping result, we use the traditional least squares solver to minimize the difference between the gradient obtained by PGENet and the gradient of the unwrapped phase. Experiments on simulated and real InSAR data demonstrated that the proposed method outperforms the other five well-established phase unwrapping methods and is robust to noise. |
| first_indexed | 2024-03-10T05:05:54Z |
| format | Article |
| id | doaj.art-498b800f92714ed689fc8b3bb2c088d7 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T05:05:54Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-498b800f92714ed689fc8b3bb2c088d72023-11-23T01:19:29ZengMDPI AGRemote Sensing2072-42922021-11-011322456410.3390/rs13224564A Robust InSAR Phase Unwrapping Method via Phase Gradient Estimation NetworkLiming Pu0Xiaoling Zhang1Zenan Zhou2Liang Li3Liming Zhou4Jun Shi5Shunjun Wei6School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaPhase unwrapping is a critical step in synthetic aperture radar interferometry (InSAR) data processing chains. In almost all phase unwrapping methods, estimating the phase gradient according to the phase continuity assumption (PGE-PCA) is an essential step. The phase continuity assumption is not always satisfied due to the presence of noise and abrupt terrain changes; therefore, it is difficult to get the correct phase gradient. In this paper, we propose a robust least squares phase unwrapping method that works via a phase gradient estimation network based on the encoder–decoder architecture (PGENet) for InSAR. In this method, from a large number of wrapped phase images with topography features and different levels of noise, the deep convolutional neural network can learn global phase features and the phase gradient between adjacent pixels, so a more accurate and robust phase gradient can be predicted than that obtained by PGE-PCA. To get the phase unwrapping result, we use the traditional least squares solver to minimize the difference between the gradient obtained by PGENet and the gradient of the unwrapped phase. Experiments on simulated and real InSAR data demonstrated that the proposed method outperforms the other five well-established phase unwrapping methods and is robust to noise.https://www.mdpi.com/2072-4292/13/22/4564interferometric synthetic aperture radardeep convolutional neural networkphase unwrapping |
| spellingShingle | Liming Pu Xiaoling Zhang Zenan Zhou Liang Li Liming Zhou Jun Shi Shunjun Wei A Robust InSAR Phase Unwrapping Method via Phase Gradient Estimation Network Remote Sensing interferometric synthetic aperture radar deep convolutional neural network phase unwrapping |
| title | A Robust InSAR Phase Unwrapping Method via Phase Gradient Estimation Network |
| title_full | A Robust InSAR Phase Unwrapping Method via Phase Gradient Estimation Network |
| title_fullStr | A Robust InSAR Phase Unwrapping Method via Phase Gradient Estimation Network |
| title_full_unstemmed | A Robust InSAR Phase Unwrapping Method via Phase Gradient Estimation Network |
| title_short | A Robust InSAR Phase Unwrapping Method via Phase Gradient Estimation Network |
| title_sort | robust insar phase unwrapping method via phase gradient estimation network |
| topic | interferometric synthetic aperture radar deep convolutional neural network phase unwrapping |
| url | https://www.mdpi.com/2072-4292/13/22/4564 |
| work_keys_str_mv | AT limingpu arobustinsarphaseunwrappingmethodviaphasegradientestimationnetwork AT xiaolingzhang arobustinsarphaseunwrappingmethodviaphasegradientestimationnetwork AT zenanzhou arobustinsarphaseunwrappingmethodviaphasegradientestimationnetwork AT liangli arobustinsarphaseunwrappingmethodviaphasegradientestimationnetwork AT limingzhou arobustinsarphaseunwrappingmethodviaphasegradientestimationnetwork AT junshi arobustinsarphaseunwrappingmethodviaphasegradientestimationnetwork AT shunjunwei arobustinsarphaseunwrappingmethodviaphasegradientestimationnetwork AT limingpu robustinsarphaseunwrappingmethodviaphasegradientestimationnetwork AT xiaolingzhang robustinsarphaseunwrappingmethodviaphasegradientestimationnetwork AT zenanzhou robustinsarphaseunwrappingmethodviaphasegradientestimationnetwork AT liangli robustinsarphaseunwrappingmethodviaphasegradientestimationnetwork AT limingzhou robustinsarphaseunwrappingmethodviaphasegradientestimationnetwork AT junshi robustinsarphaseunwrappingmethodviaphasegradientestimationnetwork AT shunjunwei robustinsarphaseunwrappingmethodviaphasegradientestimationnetwork |