SAR Image Change Detection via Spatial Metric Learning with an Improved Mahalanobis Distance

TL;DR

This paper introduces a spatial metric learning approach using an improved Mahalanobis distance to generate more robust difference images for SAR change detection, effectively handling speckle noise and registration errors.

Contribution

The paper proposes a novel spatial metric learning method that incorporates spatial context and an optimized Mahalanobis distance for improved SAR change detection.

Findings

Outperforms state-of-the-art methods on four challenging datasets

Robust to speckle noise and registration errors

Produces more accurate difference images

Abstract

The log-ratio (LR) operator has been widely employed to generate the difference image for synthetic aperture radar (SAR) image change detection. However, the difference image generated by this pixel-wise operator can be subject to SAR images speckle and unavoidable registration errors between bitemporal SAR images. In this letter, we proposed a spatial metric learning method to obtain a difference image more robust to the speckle by learning a metric from a set of constraint pairs. In the proposed method, spatial context is considered in constructing constraint pairs, each of which consists of patches in the same location of bitemporal SAR images. Then, a semi-definite positive metric matrix $\bf M$ can be obtained by the optimization with the max-margin criterion. Finally, we verify our proposed method on four challenging datasets of bitemporal SAR images. Experimental results demonstrate that the difference map obtained by our proposed method outperforms than other state-of-art methods.