Reciprocal translation between SAR and optical remote sensing images with cascaded-residual adversarial networks

作     者：Shilei FU Feng XU Ya-Qiu JIN Shilei FU;Feng XU;Ya-Qiu JIN

作者机构：Key Lab for Information Science of Electromagnetic Waves (MoE)Fudan University 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2021年第64卷第2期

页      面：154-168页

核心收录：

学科分类：12[管理学] 080904[工学-电磁场与微波技术] 0808[工学-电气工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 0810[工学-信息与通信工程] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 081105[工学-导航、制导与控制] 0835[工学-软件工程] 081001[工学-通信与信息系统] 081002[工学-信号与信息处理] 0825[工学-航空宇航科学与技术] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported in part by National Key R&D Program of China (Grant No. 2017YFB0502703) Natural Science Foundation of China (Grant Nos. 61822107, 61571134) 

主　　题：synthetic aperture radar generative adversarial network (GAN) image translation cascaded residual connection Frechet inception distance 

摘      要：Despite the advantages of all-weather and all-day high-resolution imaging, synthetic aperture radar(SAR) images are much less viewed and used by general people because human vision is not adapted to microwave scattering phenomenon. However, expert interpreters can be trained by comparing side-byside SAR and optical images to learn the mapping rules from SAR to optical. This paper attempts to develop machine intelligence that is trainable with large-volume co-registered SAR and optical images to translate SAR images to optical version for assisted SAR image interpretation. Reciprocal SAR-optical image translation is a challenging task because it is a raw data translation between two physically very different sensing modalities. Inspired by recent progresses in image translation studies in computer vision,this paper tackles the problem of SAR-optical reciprocal translation with an adversarial network scheme where cascaded residual connections and hybrid L1-GAN loss are employed. It is trained and tested on both spaceborne Gaofen-3(GF-3) and airborne Uninhabited Airborne Vehicle Synthetic Aperture Radar(UAVSAR) images. Results are presented for datasets of different resolutions and polarizations and compared with other state-of-the-art methods. The Frechet inception distance(FID) is used to quantitatively evaluate the translation performance. The possibility of unsupervised learning with unpaired/unregistered SAR and optical images is also explored. Results show that the proposed translation network works well under many scenarios and it could potentially be used for assisted SAR interpretation.