A Interferogram Denoising Method Based on Convolutional Neural Network

TAO Liqing; HUANG Guoman; YANG Shucheng; WANG Tongtong; SHENG Huijun; FAN Haitao

doi:10.13203/j.whugis20200589

Volume 48 Issue 4

Apr. 2023

Turn off MathJax

Article Contents

Abstract

References

Geomatics and Information Science of Wuhan University > 2023 > 48(4): 559-567. > DOI: 10.13203/j.whugis20200589

TAO Liqing, HUANG Guoman, YANG Shucheng, WANG Tongtong, SHENG Huijun, FAN Haitao. A Interferogram Denoising Method Based on Convolutional Neural Network[J]. Geomatics and Information Science of Wuhan University, 2023, 48(4): 559-567. DOI: 10.13203/j.whugis20200589

Citation:

PDF (65621 KB)

A Interferogram Denoising Method Based on Convolutional Neural Network

1.
Chinese Academy of Surveying and Mapping, Beijing 100039, China
2.
China Academy of Space Technology Hangzhou Institute, Hangzhou 310001, China
3.
College of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao 266590, China
4.
Sehool of Marine Technology and Geomatics, Jiangsu Ocean University, Lianyungang 222005, China

More Information

Received Date: October 28, 2021
Available Online: April 16, 2023
Published Date: April 04, 2023

Graphical Abstract

Abstract

Abstract

Objectives Interferogram filtering is the key to the subsequent processing steps of interferometric synthetic aperture radar, such as phase unwrapping and geocoding. However, the existing filtering methods can't retain features in dense fringes and accurately estimate phase in low-coherence regions. The convolutional neural networks (CNN) is introduced to learn noise features and solve this problem.
Methods First, we selected a certain number of interferograms as samples, and divided them into training set, test set, and validation set. Second, we preprocessed the training set samples, and cut the preprocessed training set interferograms into small fixed-size block and randomly extract it as a model training sample, used the above steps to train the autoencoder filter model, after a certain number of iterations, the model was fitted.
Results Experiments were carried out on spaceborne imaging radar-C-band synthetic aperture radar data and Sentinel-1A data. Our proposed method was compared with Goldstein filter, mean filter, Lee filter, Frost filter, and improved denoising convolutional neural network (DnCNN). Goldstein filter can remove most of the noise while maintaining fringes edge, has good denoising ability. Mean filter performs well in high-coherence areas, but performs poorly in low-coherence areas, and can't filter noise well. Lee filter maintains it well image resolution, but the denoising effect is weak, and it can be seen from the filtering results that there is still a lot of noise. Frost filtering is weak in low-coherence areas and there is a lot of noise, but the fringe edges are well maintained in high-coherence areas. The improved DnCNN filter can significantly eliminate the noise, but it can't distinguish the fringe edge and the noise well. Our proposed method can suppress the noise very well, and it can maintain the fringe edge well in the low-coherence area and the high-coherence area.
Conclusions This proposed method can greatly improve the phase quality of the interferogram, suppress the noise to a greater extent, and restore more image details and maintain the edge continuity of the interference fringe.
- interferogram,
- convolutional neural network (CNN),
- unsupervised learning,
- phase noise

FullText(HTML)

References (19)

References

[1]	郭际明, 黄长军, 喻小东, 等. 利用BEMD-自适应滤波去除SAR干涉图噪声[J]. 武汉大学学报(信息科学版), 2014, 39(4): 422-427. doi: 10.13203/j.whugis20120013 Guo Jiming, Huang Changjun, Yu Xiaodong, et al. Interferogram Denoising Method Based on BEMD and Adaptive Filter[J]. Geomatics and Information Science of Wuhan University, 2014, 39(4): 422-427. doi: 10.13203/j.whugis20120013
[2]	Goldstein R M, Werner C L. Radar Interferogram Filtering for Geophysical Applications[J]. Geophysical Research Letters, 1998, 25(21): 4035-4038. doi: 10.1029/1998GL900033
[3]	Baran I, Stewart M P, Kampes B M, et al. A Modification to the Goldstein Radar Interferogram Filter[J]. IEEE Transactions on Geoscience and Remote Sensing, 2003, 41(9): 2114-2118. doi: 10.1109/TGRS.2003.817212
[4]	Sun Q, Li Z W, Zhu J J, et al. Improved Goldstein Filter for InSAR Noise Reduction Based on Local SNR[J]. Journal of Central South University, 2013, 20(7): 1896-1903. doi: 10.1007/s11771-013-1688-3
[5]	Lee J S. Digital Image Enhancement and Noise Filtering by Use of Local Statistics[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1980, 2(2): 165-168.
[6]	余景波, 刘国林, 曹振坦, 等. 综合滤波InSAR干涉图去噪实验分析[J]. 测绘科学, 2013, 38(5): 129-132. https://www.cnki.com.cn/Article/CJFDTOTAL-CHKD201305042.htm Yu Jingbo, Liu Guolin, Cao Zhentan, et al. Experimental Analysis on Integrated Filtering Denoising of InSAR Interferogram[J]. Science of Surveying and Mapping, 2013, 38(5): 129-132. https://www.cnki.com.cn/Article/CJFDTOTAL-CHKD201305042.htm
[7]	Frost V S, Stiles J A, Shanmugan K S, et al. A Model for Radar Images and Its Application to Adaptive Digital Filtering of Multiplicative Noise[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1982, 4(2): 157-166.
[8]	卢宏涛, 张秦川. 深度卷积神经网络在计算机视觉中的应用研究综述[J]. 数据采集与处理, 2016, 31(1): 1-17. https://www.cnki.com.cn/Article/CJFDTOTAL-SJCJ201601001.htm Lu Hongtao, Zhang Qinchuan. Applications of Deep Convolutional Neural Network in Computer Vision[J]. Journal of Data Acquisition and Processing, 2016, 31(1): 1-17. https://www.cnki.com.cn/Article/CJFDTOTAL-SJCJ201601001.htm
[9]	Bengio Y. Learning Deep Architectures for AI[J]. Foundations and Trends in Machine Learning, 2009, 2(1): 1-127. doi: 10.1561/2200000006
[10]	Zhang K, Zuo W M, Chen Y J, et al. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising[J]. IEEE Transactions on Image Processing: A Publication of the IEEE Signal Processing Society, 2017, 26(7): 3142-3155. doi: 10.1109/TIP.2017.2662206
[11]	Li S, Xu H P, Gao S, et al. An Interferometric Phase Noise Reduction Method Based on Modified Denoising Convolutional Neural Network[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13: 4947-4959. doi: 10.1109/JSTARS.2020.3017808
[12]	周聪, 曾祥芝, 袁静, 等. 利用深度自编码算法的地震脉冲信号检测方法[J]. 武汉大学学报(信息科学版), 2020, 45(7): 980-987. doi: 10.13203/j.whugis20180348 Zhou Cong, Zeng Xiangzhi, Yuan Jing, et al. Earthquake Pulselike Records Detection Based on Deep Autoencoder[J]. Geomatics and Information Science of Wuhan University, 2020, 45(7): 980-987. doi: 10.13203/j.whugis20180348
[13]	Cai B, Liang D N, Dong Z. A New Adaptive Multiresolution Noise-Filtering Approach for SAR Interferometric Phase Images[J]. IEEE Geoscience and Remote Sensing Letters, 2008, 5(2): 266-270. doi: 10.1109/LGRS.2008.915942
[14]	Mestre-Quereda A, Lopez-Sanchez J M, Selva J, et al. An Improved Phase Filter for Differential SAR Interferometry Based on an Iterative Method[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(8): 4477-4491. doi: 10.1109/TGRS.2018.2820725
[15]	葛芸, 江顺亮, 叶发茂, 等. 基于ImageNet预训练卷积神经网络的遥感图像检索[J]. 武汉大学学报(信息科学版), 2018, 43(1): 67-73. doi: 10.13203/j.whugis20150498 Ge Yun, Jiang Shunliang, Ye Famao, et al. Remote Sensing Image Retrieval Using Pre-trained Convolutional Neural Networks Based on ImageNet[J]. Geomatics and Information Science of Wuhan University, 2018, 43(1): 67-73. doi: 10.13203/j.whugis20150498
[16]	Wu Z H, Cui Y D. Edge Missing Image Inpainting with Compression-Decompression Network in Low Similarity Images[J]. Machine Vision and Applications, 2021, 32(1): 37.
[17]	Shakya A, Biswas M, Pal M. Parametric Study of Convolutional Neural Network Based Remote Sensing Image Classification[J]. International Journal of Remote Sensing, 2021, 42(7): 2663-2685.
[18]	He K M, Zhang X Y, Ren S Q, et al. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification[C]// IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2016.
[19]	López-Antequera M, Leyva Vallina M, Strisciuglio N, et al. Place and Object Recognition by CNN-Based COSFIRE Filters[J]. IEEE Access, 2019, 7: 66157-66166.

[1]	SONG Weiwei, SONG Qisheng, HE Qianqian, GONG Xiaopeng, GU Shengfeng. Analysis of PPP-B2b Positioning Performance Enhanced by High-Precision Ionospheric Products[J]. Geomatics and Information Science of Wuhan University, 2024, 49(9): 1517-1526. DOI: 10.13203/j.whugis20230030
[2]	ZHU Shaolin, YUE Dongjie, HE Lina, CHEN Jian, LIU Shengnan. BDS-2/BDS-3 Joint Triple-Frequency Precise Point Positioning Models and Bias Characteristic Analysis[J]. Geomatics and Information Science of Wuhan University, 2023, 48(12): 2049-2059. DOI: 10.13203/j.whugis20210273
[3]	ZHAO Qile, TAO Jun, GUO Jing, CHEN Guo, XU Xiaolong, ZHANG Qiang, ZHANG Gaojian, XU Shengyi, LI Junqiang. Wide-Area Instantaneous cm-Level Precise Point Positioning: Method and Service System[J]. Geomatics and Information Science of Wuhan University, 2023, 48(7): 1058-1069. DOI: 10.13203/j.whugis20230202
[4]	YAN Zhongbao, ZHANG Xiaohong. Partial Ambiguity Resolution Method and Results Analysis for GNSS Uncombined PPP[J]. Geomatics and Information Science of Wuhan University, 2022, 47(6): 979-989. DOI: 10.13203/j.whugis20220025
[5]	ZHANG Hui, HAO Jinming, LIU Weiping, ZHOU Rui, TIAN Yingguo. GPS/BDS Precise Point Positioning Model with Receiver DCB Parameters for Raw Observations[J]. Geomatics and Information Science of Wuhan University, 2019, 44(4): 495-500, 592. DOI: 10.13203/j.whugis20170119
[6]	ZHANG Xiaohong, LIU Gen, GUO Fei, LI Xin. Model Comparison and Performance Analysis of Triple-frequency BDS Precise Point Positioning[J]. Geomatics and Information Science of Wuhan University, 2018, 43(12): 2124-2130. DOI: 10.13203/j.whugis20180078
[7]	ZHANG Xiaohong, CAI Shixiang, LI Xingxing, GUO Fei. Accuracy Analysis of Time and Frequency Transfer Based on Precise Point Positioning[J]. Geomatics and Information Science of Wuhan University, 2010, 35(3): 274-278.
[8]	ZHANG Xiaohong, GUO Fei, LI Xingxing, LIN Xiaojing. Study on Precise Point Positioning Based on Combined GPS and GLONASS[J]. Geomatics and Information Science of Wuhan University, 2010, 35(1): 9-12.
[9]	FU Jianhong, YUAN Xiuxiao. Influence of GPS Base Station on Accuracy of Positioning by Airborne Position and Orientation System[J]. Geomatics and Information Science of Wuhan University, 2007, 32(5): 398-401.
[10]	Huang Shengxiang, Zhang Yan. Estimation of Accuracy Indicators for GPS Relative Positioning[J]. Geomatics and Information Science of Wuhan University, 1997, 22(1): 47-50.

Cited By

Cited by

Periodical cited type(22)

1.	肖斌宸，叶飞，叶险峰，曾翔强. 电离层和地形复杂区域北斗/GNSS实时PPP性能及大气分析. 数据与计算发展前沿(中英文). 2025(01): 108-118 .
2.	侯诚，史俊波，苟劲松，郭际明，邹进贵. 多路径误差对BDS-3变形监测精度的影响. 大地测量与地球动力学. 2024(02): 128-133 .
3.	邓陈喜，姜维，王剑，蔡伯根. 基于北斗3号PPP-B2b信号的实时精密单点定位方法研究. 铁道学报. 2024(02): 63-73 .
4.	于合理，孙晓东，贾赞杰，武智佳，代桃高. 限制环境下的GNSS精密授时方法研究综述. 海洋测绘. 2024(02): 46-50 .
5.	许扬胤，任夏，明锋. 北斗三号PPP-B2b信号精密单点定位服务可用性分析. 全球定位系统. 2024(03): 10-19 .
6.	肖恭伟，卞逸驰，何在民，广伟，尹翔飞，张润芝. 北斗三号PPP-B2b差分码偏差对UPPP解算的影响. 西安邮电大学学报. 2024(02): 1-10 .
7.	宋伟伟，宋啟晟，何倩倩，龚晓鹏，辜声峰. 高精度电离层产品增强PPP-B2b定位性能分析. 武汉大学学报(信息科学版). 2024(09): 1517-1526 .
8.	索世恒，韩昆，张永峰. 伽利略高精度服务产品与其全球定位性能评估. 地理空间信息. 2024(11): 100-104+121 .
9.	孙爽，王敏，刘长建，孟欣，季锐. PPP-B2b服务钟差常数偏差特性及对定位的影响分析. 测绘科学. 2023(01): 8-15 .
10.	郭文飞，朱萌萌，辜声峰，左鸿铭，陈金鑫. GNSS精密时频接收机时钟调控模型与参数设计方法. 武汉大学学报(信息科学版). 2023(07): 1126-1133 .
11.	唐守普，吴文坛，夏振营，史进志，赵婉清，莫雁寒. 北斗三号PPP-B2b独立定位分析与应用. 河北省科学院学报. 2023(03): 61-69 .
12.	赵淑洁，赵当丽，黄媛媛，纪元法. 基于PPP-B2b改正产品的北斗实时精密星历精度分析. 时间频率学报. 2023(02): 141-149 .
13.	张润芝，何在民，马红皎，武建锋，广伟，肖恭伟. 北斗三号PPP-B2b信号跟踪环路的极点分布法设计. 时间频率学报. 2023(02): 161-169 .
14.	姚夏，李志敏，吴如楠，毛飞宇，龚晓鹏. 北斗三号PPP-B2b信号时间同步性能分析. 导航定位学报. 2023(04): 84-89 .
15.	史俊波，董新莹，欧阳晨皓，彭文杰，姚宜斌. 基于北斗三号PPP服务的快速静态和低动态定位性能分析. 大地测量与地球动力学. 2023(10): 997-1002 .
16.	韩晓红，孙保琪，张喆，周红源，杨海彦，赵当丽，杨旭海. 基于北斗三号PPP-B2b轨道的实时精密共视时间传递. 导航定位与授时. 2023(04): 103-111 .
17.	肖鹏，孙付平，张伦东，肖凯，商向永. 北斗三号PPP-B2b服务实时动态定位性能分析. 导航定位学报. 2023(05): 21-28 .
18.	刘杨，曾安敏，郑翠娥，江鹏，刘焱雄. 广播式远程精密水下导航定位技术. 哈尔滨工程大学学报. 2023(11): 1987-1995 .
19.	王林伟，周长江，余海锋，岳彩亚. 全球精密单点定位性能评估. 导航定位与授时. 2023(06): 86-92 .
20.	赵泉涌，潘树国，缪巍巍，沈超，高旺，赵庆. PPP-B2b常数偏差实时改正后的多频单历元定位. 测绘科学. 2023(11): 61-68 .
21.	彭松，刘建坤，张云龙，常丹，孙兆辉. 基于北斗三号远程监测系统的公路岩质边坡开挖变形分析. 科学技术与工程. 2022(33): 14898-14906 .
22.	余德荧，金际航，刘一，边少锋. 基于北斗三号PPP-B2b信号的海上精密定位试验分析. 海洋测绘. 2022(06): 51-55+64 .

Other cited types(9)

Get Citation

PDF

XML

Article views (501) PDF downloads (116) Cited by(31)

A Interferogram Denoising Method Based on Convolutional Neural Network

Abstract

References

Related Articles

Cited by

Periodical cited type(22)

Other cited types(9)

Catalog

Related

A Interferogram Denoising Method Based on Convolutional Neural Network

Abstract

References

Related Articles

Cited by

Periodical cited type(22)

Other cited types(9)

Catalog

Related

Export File

Citation

Format

Content