Change Detection in Synthetic Aperture Radar Images Using a Dual-Domain Network

Change detection from synthetic aperture radar (SAR) imagery is a critical yet challenging task. Existing methods mainly focus on feature extraction in spatial domain, and little attention has been paid to frequency domain. Furthermore, patch-wise analysis, some noisy features the marginal region may be introduced. To tackle above two challenges, we propose Dual-Domain Network. Specifically, take discrete cosine transform domain into consideration reshaped DCT coefficients are integrated proposed model as branch. Feature representations both exploited alleviate speckle noise. In addition, further multi-region convolution module, which emphasizes central of each patch. The contextual information modeled adaptively. experimental results three SAR datasets demonstrate effectiveness model. Our codes available at https://github.com/summitgao/SAR_CD_DDNet.