Toward High-Confidence Homogeneous Features: Partial Neighborhood Ratio Based Difference Image for SAR Change Detection

Abstract

The inherent speckle noise in synthetic aperture radar (SAR) images limits the accuracy of SAR image change detection. As a crucial step in unsupervised change detection, existing difference map generation methods primarily utilize neighborhood information to counteract the interference caused by speckle noise. However, pixels within the neighborhood can themselves be affected by heterogeneous pixels and noise. Therefore, this letter proposes a difference map generation method, partial neighborhood ratio (PNR), which relies on high-confidence homogeneous pixels within the neighborhood for difference calculation. Specifically, under the assumption that the local neighborhood of SAR images follows a normal distribution, we develop a method for selecting high-confidence homogeneous pixels. This method quantifies interneighborhood dissimilarity by leveraging the statistical features of predominantly homogeneous pixel clusters within an adaptive framework, thereby reducing the impact of noise and enhancing the accuracy of difference expression. Experimental results demonstrate the superior performance of the proposed PNR. The change detection results, obtained by applying both manual trial-and-error and dual-domain network (DDNet) on three SAR datasets, have validated the effectiveness of the proposed algorithm.