Change Alignment-Based Graph Structure Learning for Unsupervised Heterogeneous Change Detection

Heterogeneous change detection (HCD) in remote sensing has gained significant attention. Heterogeneous images come from different sensors, which cannot be compared directly to detect changes. This letter proposes a change alignment-based graph structure learning (CAGSL) method for unsupervised HCD, which detects changes by calculating forward and backward structure differences. To achieve this objective, CAGSL incorporates two pivotal improvements. First, CAGSL utilizes a graph autoencoder (GAE) to optimize the graph structure, enabling a more accurate representation of the topological relationships between the real land covers. Second, CAGSL introduces a change alignment constraint based on the HCD task property that the forward and backward structural differences represent the same change event to enhance the optimization of the graph structure. Subsequently, the optimized graph structure is used to compute the structure difference images through graph mapping. Finally, the change map (CM) is obtained through Otsu segmentation. Experimental results demonstrate the effectiveness of the proposed CAGSL when compared to some state-of-the-art (SOTA) methods.

Automated summary

This paper proposes a new method called CAGSL for heterogeneous change detection, which uses graph structure learning and change alignment constraint to improve the detection accuracy, and its effectiveness is demonstrated through experiments.