Affiliation:
1. State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an 710071, China
2. Beijing Institute of Control Engineering, Beijing 100190, China
Abstract
Synthetic aperture radar (SAR) is prevalent in the remote sensing field but is difficult to interpret by human visual perception. Recently, SAR-to-optical (S2O) image conversion methods have provided a prospective solution. However, since there is a substantial domain difference between optical and SAR images, they suffer from low image quality and geometric distortion in the produced optical images. Motivated by the analogy between pixels during the S2O image translation and molecules in a heat field, a thermodynamics-inspired network for SAR-to-optical image translation (S2O-TDN) is proposed in this paper. Specifically, we design a third-order finite difference (TFD) residual structure in light of the TFD equation of thermodynamics, which allows us to efficiently extract inter-domain invariant features and facilitate the learning of nonlinear translation mapping. In addition, we exploit the first law of thermodynamics (FLT) to devise an FLT-guided branch that promotes the state transition of the feature values from an unstable diffusion state to a stable one, aiming to regularize the feature diffusion and preserve image structures during S2O image translation. S2O-TDN follows an explicit design principle derived from thermodynamic theory and enjoys the advantage of explainability. Experiments on the public SEN1-2 dataset show the advantages of the proposed S2O-TDN over the current methods with more delicate textures and higher quantitative results.
Funder
National Natural Science Foundation of China
Young Elite Scientists Sponsorship Program by CAST
Joint Laboratory for Innovation in Satellite-Borne Computers and Electronics Technology Open Fund 2023
Subject
General Earth and Planetary Sciences
Reference74 articles.
1. SAR-to-optical image translation based on improved CGAN;Yang;Pattern Recognit.,2022
2. Ray-tracing simulation techniques for understanding high-resolution SAR images;Auer;IEEE Trans. Geosci. Remote Sens.,2009
3. Deep SAR Imaging and Motion Compensation;Pu;IEEE Trans. Image Process.,2021
4. Analysis of speckle noise contribution on wavelet decomposition of SAR images;Simard;IEEE Trans. Geosci. Remote Sens.,1998
5. Guo, Z., Guo, H., Liu, X., Zhou, W., Wang, Y., and Fan, Y. (2022). Sar2color: Learning Imaging Characteristics of SAR Images for SAR-to-Optical Transformation. Remote Sens., 14.