A DEEP LEARNING COREGISTRATION APPROACH FOR DISTRIBUTED GEOSYNCHRONOUS SAR THREE-DIMENSIONAL DEFORMATION RETRIEVAL

Xingzhe Zhao; Yuanhao Li; Zhiyang Chen; Yuhui Xie; Cheng Hu

doi:10.1109/IGARSS52108.2023.10283370

A DEEP LEARNING COREGISTRATION APPROACH FOR DISTRIBUTED GEOSYNCHRONOUS SAR THREE-DIMENSIONAL DEFORMATION RETRIEVAL

Xingzhe Zhao
, Yuanhao Li
, Zhiyang Chen
, Yuhui Xie
, Cheng Hu

School of Information and Electronics

Beijing Institute of Technology

Research output: Contribution to journal › Conference article › peer-review

1 Citation (Scopus)

Abstract

Geosynchronous Synthetic Aperture Radar(GEO SAR) has become a hot spot because of short revisit time and wide coverage. Compared with single satellite, distributed GEO SAR provides rich observation angles which makes high-accuracy three-dimensional(3D) deformation retrieval possible. However, there are significant differences in the resolution and texture of Interferometric Synthetic Aperture Radar(InSAR) image at different observation angles, which will lead to reduced accuracy of 3D deformation retrieval. In terms of problems above, Pseudo-CycleGAN is proposed in this paper based on phase unwrapping Deep Neural Network(DNN) and CycleGan. It can improve the accuracy of 3D deformation retrieval through texture assimilation of interferogram with high phase accuracy.

Original language	English
Pages (from-to)	1791-1794
Number of pages	4
Journal	International Geoscience and Remote Sensing Symposium (IGARSS)
DOIs	https://doi.org/10.1109/IGARSS52108.2023.10283370
Publication status	Published - 2023
Event	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 - Pasadena, United States Duration: 16 Jul 2023 → 21 Jul 2023

Keywords

3D deformation retrieval
GEO SAR
Pseudo-CycleGan

Access to Document

10.1109/IGARSS52108.2023.10283370

Cite this

@article{43e47a96810f40b0b74b3c9ed6a441b8,

title = "A DEEP LEARNING COREGISTRATION APPROACH FOR DISTRIBUTED GEOSYNCHRONOUS SAR THREE-DIMENSIONAL DEFORMATION RETRIEVAL",

abstract = "Geosynchronous Synthetic Aperture Radar(GEO SAR) has become a hot spot because of short revisit time and wide coverage. Compared with single satellite, distributed GEO SAR provides rich observation angles which makes high-accuracy three-dimensional(3D) deformation retrieval possible. However, there are significant differences in the resolution and texture of Interferometric Synthetic Aperture Radar(InSAR) image at different observation angles, which will lead to reduced accuracy of 3D deformation retrieval. In terms of problems above, Pseudo-CycleGAN is proposed in this paper based on phase unwrapping Deep Neural Network(DNN) and CycleGan. It can improve the accuracy of 3D deformation retrieval through texture assimilation of interferogram with high phase accuracy.",

keywords = "3D deformation retrieval, GEO SAR, Pseudo-CycleGan",

author = "Xingzhe Zhao and Yuanhao Li and Zhiyang Chen and Yuhui Xie and Cheng Hu",

note = "Publisher Copyright: {\textcopyright}2023 IEEE.; 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 ; Conference date: 16-07-2023 Through 21-07-2023",

year = "2023",

doi = "10.1109/IGARSS52108.2023.10283370",

language = "English",

pages = "1791--1794",

journal = "International Geoscience and Remote Sensing Symposium (IGARSS)",

issn = "2153-6996",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - A DEEP LEARNING COREGISTRATION APPROACH FOR DISTRIBUTED GEOSYNCHRONOUS SAR THREE-DIMENSIONAL DEFORMATION RETRIEVAL

AU - Zhao, Xingzhe

AU - Li, Yuanhao

AU - Chen, Zhiyang

AU - Xie, Yuhui

AU - Hu, Cheng

PY - 2023

Y1 - 2023

N2 - Geosynchronous Synthetic Aperture Radar(GEO SAR) has become a hot spot because of short revisit time and wide coverage. Compared with single satellite, distributed GEO SAR provides rich observation angles which makes high-accuracy three-dimensional(3D) deformation retrieval possible. However, there are significant differences in the resolution and texture of Interferometric Synthetic Aperture Radar(InSAR) image at different observation angles, which will lead to reduced accuracy of 3D deformation retrieval. In terms of problems above, Pseudo-CycleGAN is proposed in this paper based on phase unwrapping Deep Neural Network(DNN) and CycleGan. It can improve the accuracy of 3D deformation retrieval through texture assimilation of interferogram with high phase accuracy.

AB - Geosynchronous Synthetic Aperture Radar(GEO SAR) has become a hot spot because of short revisit time and wide coverage. Compared with single satellite, distributed GEO SAR provides rich observation angles which makes high-accuracy three-dimensional(3D) deformation retrieval possible. However, there are significant differences in the resolution and texture of Interferometric Synthetic Aperture Radar(InSAR) image at different observation angles, which will lead to reduced accuracy of 3D deformation retrieval. In terms of problems above, Pseudo-CycleGAN is proposed in this paper based on phase unwrapping Deep Neural Network(DNN) and CycleGan. It can improve the accuracy of 3D deformation retrieval through texture assimilation of interferogram with high phase accuracy.

KW - 3D deformation retrieval

KW - GEO SAR

KW - Pseudo-CycleGan

UR - https://www.scopus.com/pages/publications/105030869915

U2 - 10.1109/IGARSS52108.2023.10283370

DO - 10.1109/IGARSS52108.2023.10283370

M3 - Conference article

AN - SCOPUS:105030869915

SN - 2153-6996

SP - 1791

EP - 1794

JO - International Geoscience and Remote Sensing Symposium (IGARSS)

JF - International Geoscience and Remote Sensing Symposium (IGARSS)

T2 - 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023

Y2 - 16 July 2023 through 21 July 2023

ER -

A DEEP LEARNING COREGISTRATION APPROACH FOR DISTRIBUTED GEOSYNCHRONOUS SAR THREE-DIMENSIONAL DEFORMATION RETRIEVAL

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this