Academic Journal

Multiorder Graph Convolutional Network With Channel Attention for Hyperspectral Change Detection

التفاصيل البيبلوغرافية
العنوان: Multiorder Graph Convolutional Network With Channel Attention for Hyperspectral Change Detection
المؤلفون: Yuxiang Zhang, Rui Miao, Yanni Dong, Bo Du
المصدر: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 1523-1534 (2024)
بيانات النشر: IEEE, 2024.
سنة النشر: 2024
المجموعة: LCC:Ocean engineering
LCC:Geophysics. Cosmic physics
مصطلحات موضوعية: Change detection (CD), graph convolutional network (GCN), hyperspectral images (HSI), Ocean engineering, TC1501-1800, Geophysics. Cosmic physics, QC801-809
الوصف: Hyperspectral change detection (CD) aims to obtain the change information of objects in the multitemporal hyperspectral images (HSIs). Recently, with the advantages in fully extracting the image features of irregular areas, the graph convolutional network (GCN) has attracted increasing attention for hyperspectral CD. The existing GCN-based CD methods usually use a graph structure constructed by superpixels to reduce the computational cost, which ignores the multiorder difference information among graph nodes and the local difference information within superpixels. To address these problems, this article proposes an efficient multiorder GCN with a channel attention module (CAM) for hyperspectral CD. Specifically, the multiorder GCN module is designed by repeatedly mixing the feature representations of neighborhoods. The CAM is then proposed to enhance the difference features of bitemporal HSIs. After that, the pixel-wise CD is accomplished by a lightweight feature fusion module and a fully connected layer. Experiments on three hyperspectral datasets illustrated the effectiveness of the proposed algorithm.
نوع الوثيقة: article
وصف الملف: electronic resource
اللغة: English
تدمد: 2151-1535
Relation: https://ieeexplore.ieee.org/document/10342770/; https://doaj.org/toc/2151-1535
DOI: 10.1109/JSTARS.2023.3339238
URL الوصول: https://doaj.org/article/d87083d30df349abb14ef5d126014b4f
رقم الانضمام: edsdoj.87083d30df349abb14ef5d126014b4f
قاعدة البيانات: Directory of Open Access Journals
الوصف
تدمد:21511535
DOI:10.1109/JSTARS.2023.3339238