DEN: A New Method for SAR and Optical Image Fusion and Intelligent Classification

Abstract

Synthetic aperture radar (SAR) and optical images possess complementary strengths, offering rich spatial and spectral information. The intelligent classification of features through image fusion of SAR and optical presents both opportunities and challenges. However, fusion and intelligent classification encounter hurdles. Different physical properties and imaging principles between SAR and optical images often lead to sensor property mismatches, causing information loss. Moreover, optical images are susceptible to weather conditions, while SAR images suffer from scattering noise interference. In addition, the nonuniform distribution of feature categories results in sample imbalance. To address these problems, this article proposed a new fusion network structure dual-encoder net (DEN). First, without increasing the model complexity, considering the differences in the performance of features under different sensors, this network was keyed to a composition of two encoders that were able to utilize their respective features to encode and reduce the impact of modal differences. Second, a detail attention module (DAM) was constructed to capture the detailed information that was obscured by the optical image and acquired by the SAR image. Finally, a new loss function, comprising weighted information loss, pixel loss, and noise loss, was introduced to mitigate sample imbalance, retain key information, and reduce noise effects. The experimental results showed that the proposed method outperforms the current popular image fusion methods, and the model complexity was improved by 15.3% while the overall accuracy (OA) was improved by 2.6%, and the entropy, peak signal-to-noise ratio (PSNR), and mean square error (MSE) were improved by 29%, 27%, and 7%, respectively.