SAR-to-Optical Image Translating Through Generate-Validate Adversarial Networks

被引：13
作者：
Shi, Hao [1 ,2 ]
Zhang, Bocheng [1 ,2 ]
Wang, Yupei [1 ,2 ]
Cui, Zihan [1 ,2 ]
Chen, Liang [1 ,2 ]
机构：
[1] Beijing Inst Technol, Beijing Key Lab Embedded Real Time Informat Proc, Beijing 100081, Peoples R China
[2] Beijing Inst Technol, Chongqing Innovat Ctr, Chongqing 401135, Peoples R China
来源：
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2022年 / 19卷
基金：
中国国家自然科学基金;
关键词：
Generators; Optical imaging; Radar polarimetry; Convolution; Synthetic aperture radar; Optical sensors; Image edge detection; Generative adversarial networks (GVANs); synthetic aperture radar (SAR); SAR-to-optical image translating; U-Net;
D O I：
10.1109/LGRS.2022.3168391
中图分类号：
P3 [地球物理学]; P59 [地球化学];
学科分类号：
0708 ; 070902 ;
摘要：
Synthetic aperture radar (SAR) has the advantages of high resolution in all-weather and all-day. However, SAR images are hard to be understood, due to their unique imaging mechanism. The SAR to optical image translation can assist in interpreting and has become a topic of growing interest in the field of remote sensing. In this letter, a SAR to optical image translation network is proposed, called generate-validate adversarial networks (GVANs). More specifically, there are two Pix2Pix networks form the cyclic structure. The validate module is employed to increase the training process and improve the edge retention ability. In order to improve multidomain images adaptability, the embedded layer is proposed. Additionally, the dilation convolution layer is employed in the generator, which is more suitable for the characteristics of SAR images. The proposed method has experimented on the SEN1-2 dataset. The result demonstrates the superiority of the proposed method over state-of-the-art methods.
引用
收藏
页数：5
相关论文
共 13 条
[1]   DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs [J].
Chen, Liang-Chieh ;
Papandreou, George ;
Kokkinos, Iasonas ;
Murphy, Kevin ;
Yuille, Alan L. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (04) :834-848
[2]   Reciprocal translation between SAR and optical remote sensing images with cascaded-residual adversarial networks [J].
Fu, Shilei ;
Xu, Feng ;
Jin, Ya-Qiu .
SCIENCE CHINA-INFORMATION SCIENCES, 2021, 64 (02)
[3]  
Hwang J, 2020, I C INF COMM TECH CO, P191, DOI [10.1109/ICTC49870.2020.9289381, 10.1109/ictc49870.2020.9289381]
[4]   Image-to-Image Translation with Conditional Adversarial Networks [J].
Isola, Phillip ;
Zhu, Jun-Yan ;
Zhou, Tinghui ;
Efros, Alexei A. .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :5967-5976
[5]   SAR Image Colorization Using Multidomain Cycle-Consistency Generative Adversarial Network [J].
Ji, Guang ;
Wang, Zhaohui ;
Zhou, Lifan ;
Xia, Yu ;
Zhong, Shan ;
Gong, Shengrong .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2021, 18 (02) :296-300
[6]  
Ley A., 2018, EUSAR 2018 12 EUR C, P396
[7]   Least Squares Generative Adversarial Networks [J].
Mao, Xudong ;
Li, Qing ;
Xie, Haoran ;
Lau, Raymond Y. K. ;
Wang, Zhen ;
Smolley, Stephen Paul .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :2813-2821
[8]   U2-Net: Going deeper with nested U-structure for salient object detection [J].
Qin, Xuebin ;
Zhang, Zichen ;
Huang, Chenyang ;
Dehghan, Masood ;
Zaiane, Osmar R. ;
Jagersand, Martin .
PATTERN RECOGNITION, 2020, 106
[9]   SAR-to-Optical Image Translation Based on Conditional Generative Adversarial Networks-Optimization, Opportunities and Limits [J].
Reyes, Mario Fuentes ;
Auer, Stefan ;
Merkle, Nina ;
Henry, Corentin ;
Schmitt, Michael .
REMOTE SENSING, 2019, 11 (17)
[10]   THE SEN1-2 DATASET FOR DEEP LEARNING IN SAR-OPTICAL DATA FUSION [J].
Schmitt, M. ;
Hughes, L. H. ;
Zhu, X. X. .
ISPRS TC I MID-TERM SYMPOSIUM INNOVATIVE SENSING - FROM SENSORS TO METHODS AND APPLICATIONS, 2018, 4-1 :141-146
12