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

Kuowei Xiao

doi:10.1109/LGRS.2023.3309301

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

2023-01-01

4

PRE

AI

DOI：10.1109/LGRS.2023.3309301

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

Change alignment

graph structure learning

heterogeneous remote sensing

unsupervised heterogeneous change detection (HCD)

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

Abstract

Journal

Organization