A CNN-BASED MULTICHANNEL INTERFEROMETRIC PHASE DENOISING METHOD APPLIED TO TOMOSAR IMAGING

被引：1

作者：

Li, Jie ^{[1
,2
,3
]}

Xu, Zhongqiu ^{[1
,2
,3
]}

Li, Zhiyuan ^{[1
,2
,3
]}

Zhang, Bingchen ^{[1
,2
,3
]}

Wu, Yirong ^{[1
,3
]}

机构：

[1] Chinese Acad Sci, Aerosp Informat Res Inst, Beijing, Peoples R China

[2] Univ Chinese Acad Sci, Key Lab Technol Geospatial Informat Proc & Applic, Beijing 100190, Peoples R China

[3] Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing 100190, Peoples R China

来源：

2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022) | 2022年

基金：

中国国家自然科学基金;

关键词：

SAR; CNN; Unsupervised learning; Image denoising; Tomography;

D O I：

10.1109/IGARSS46834.2022.9884475

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

Tomographic synthetic aperture radar (TomoSAR) is an advanced SAR interferometric technique to retrieve 3-D spatial information. However, decorrelation effects degrade the quality of interferometric phases, resulting in errors in the reconstruction. In this paper, we propose a denoising method based on the unsupervised convolution neural network (CNN) with a loss function combining the deterministic descriptive regularization and total variation (TV) term. It can improve both the accuracy and completeness of the reconstructed 3-D point clouds, which is verified by experiments on simulated and real SAR images.

引用

页码：3448 / 3451

页数：4

共 5 条

[1] Boyd S., 2004, Convex Optimization, DOI 10.1017/CBO9780511804441
[2] Budillon A, 2019, INT GEOSCI REMOTE SE, P3625, DOI [10.1109/igarss.2019.8900616, 10.1109/IGARSS.2019.8900616]
[3] Chierchia G, 2017, INT GEOSCI REMOTE SE, P5438, DOI 10.1109/IGARSS.2017.8128234
[4] Nonlocal Filtering Applied to 3-D Reconstruction of Tomographic SAR Data
D'Hondt, Olivier
Lopez-Martinez, Carlos
Guillaso, Stephane
Hellwich, Olaf
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2018, 56 (01): : 272 - 285
[5] Samiei Esfahany S., 2017, EARTH OBSERV GEOMATI, V1, P1

← 1 →