SIGNet: A Siamese Graph Convolutional Network for Multi-Class Urban Change Detection
Remote Sensing · 08.05.2023 · 15 (9) · 2464
DOI: 10.3390/rs15092464 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 08.05.2023. Verfasst von Yanpeng Zhou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 85 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China Joint Fund Key Projects, Xinjiang Uyghur Autonomous Region Key Laboratory Open Subjects, Xinjiang University Doctoral Initiation Fund.
Abstract (Originalsprache)
Detecting changes in urban areas presents many challenges, including complex features, fast-changing rates, and human-induced interference. At present, most of the research on change detection has focused on traditional binary change detection (BCD), which becomes increasingly unsuitable for the diverse urban change detection tasks as cities grow. Previous change detection networks often rely on convolutional operations, which struggle to capture global contextual information and underutilize category semantic information. In this paper, we propose SIGNet, a Siamese graph convolutional network, to solve the above problems and improve the accuracy of urban multi-class change detection (MCD) tasks. After maximizing the fusion of change differences at different scales using joint pyramidal upsampling (JPU), SIGNet uses a graph convolution-based graph reasoning (GR) method to construct static connections of urban features in space and a graph cross-attention method to couple the dynamic connections of different types of features during the change process. Experimental results show that SIGNet achieves state-of-the-art accuracy on different MCD datasets when capturing contextual relationships between different regions and semantic correlations between different categories. There are currently few pixel-level datasets in the MCD domain. We introduce a new well-labeled dataset, CNAM-CD, which is a large MCD dataset containing 2508 pairs of high-resolution images.
Förderung
- National Natural Science Foundation of China Joint Fund Key Projects
- Xinjiang Uyghur Autonomous Region Key Laboratory Open Subjects
- Xinjiang University Doctoral Initiation Fund
- Xinjiang Uygur Autonomous Region Education Department University Research Program
Zitieren
APA
Zhou, Y., Wang, J., Ding, J., Liu, B., Weng, N., & Xiao, H. (2023). SIGNet: A Siamese Graph Convolutional Network for Multi-Class Urban Change Detection. Remote Sensing, 15(9), 2464. https://doi.org/10.3390/rs15092464
Vancouver
Zhou Y, Wang J, Ding J, Liu B, Weng N, Xiao H. SIGNet: A Siamese Graph Convolutional Network for Multi-Class Urban Change Detection. Remote Sensing. 2023;15(9):2464. doi:10.3390/rs15092464
BibTeX
@article{Zhou2023,
author = {Zhou, Yanpeng and Wang, Jinjie and Ding, Jianli and Liu, Bohua and Weng, Nan and Xiao, Hongzhi},
title = {SIGNet: A Siamese Graph Convolutional Network for Multi-Class Urban Change Detection},
journal = {Remote Sensing},
year = {2023},
volume = {15},
number = {9},
pages = {2464},
doi = {10.3390/rs15092464}
}
EUVIMED