期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 60, 期 -, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2022.3229027
关键词
Change detection; graph convolutional autoencoder; graph representation learning; multimodal remote sensing images; structural relationship
类别
资金
- Japan Science and Technology Agency FOREST [JPMJFR206S]
- Japan Society for the Promotion of Science KAKENHI [22H03609]
- Japan Science and Technology Agency FOREST [JPMJFR206S]
- Japan Society for the Promotion of Science KAKENHI [22H03609]
In this paper, an unsupervised multimodal change detection method is proposed. It measures the similarity of two structural relationships by learning the graph representations and generates difference images. Finally, an adaptive fusion strategy and a postprocessing approach are employed to refine the detection results.
Unsupervised multimodal change detection is a practical and challenging topic that can play an important role in time-sensitive emergency applications. To address the challenge that multimodal remote sensing images cannot be directly compared due to their modal heterogeneity, we take advantage of two types of modality-independent structural relationships in multimodal images. In particular, we present a structural relationship graph representation learning framework for measuring the similarity of the two structural relationships. First, structural graphs are generated from preprocessed multimodal image pairs by means of an object-based image analysis approach. Then, a structural relationship graph convolutional autoencoder (SR-GCAE) is proposed to learn robust and representative features from graphs. Two loss functions aiming at reconstructing vertex information and edge information are presented to make the learned representations applicable for structural relationship similarity measurement. Subsequently, the similarity levels of two structural relationships are calculated from learned graph representations, and two difference images are generated based on the similarity levels. After obtaining the difference images, an adaptive fusion strategy is presented to fuse the two difference images. Finally, a morphological filtering-based postprocessing approach is employed to refine the detection results. Experimental results on six datasets with different modal combinations demonstrate the effectiveness of the proposed method.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据