Enhanced change detection in SAR images using DWT and optimised loss functions

Synthetic aperture radar (SAR) image change detection (CD) involves identifying changes between images captured at different times over the same geographical region. SAR provides significant advantages for disasterrelated remote sensing due to its all-weather capabilities and ability to penetrate clouds and darkness. Nevertheless, the presence of speckle noise presents a major challenge for accurate change detection. This paper introduces a robust method utilising a dual-domain model that integrates the Discrete Wavelet Transform (DWT) with biorthogonal wavelets to effectively suppress speckle noise. Furthermore, we propose an improved loss function that combines Mean Squared Error (MSE) and Kullback-Leibler Divergence (KL) to further enhance change detection accuracy. Extensive evaluations on three SAR datasets demonstrate that our approach outperforms state-of-the-art methods, significantly improving change detection accuracy.