期刊
IEEE TRANSACTIONS ON CYBERNETICS
卷 52, 期 10, 页码 10556-10569出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2021.3064571
关键词
Feature extraction; Task analysis; Spatial resolution; Satellites; Indexes; Image fusion; Data mining; Classification; deep learning; feature fusion; group spatial-spectral attention
类别
资金
- State Key Program of the National Natural Science Foundation of China [61836009, 61621005]
- Foundation for Innovative Research Groups of the National Natural Science Foundation of China [61836009, 61621005]
- Key Research and Development Program in Shaanxi Province of China [2019ZDLGY03-06]
- Major Research Plan of the National Natural Science Foundation of China [91438201, 91438103, 61801124]
- National Natural Science Foundation of China [U1701267, 62006177, 61871310, 61902298, 61573267, 61906150]
- Fund for Foreign Scholars in University Research and Teaching Program's 111 Project [B07048]
- Program for Cheung Kong Scholars and Innovative Research Team in University [IRT 15R53]
- ST Innovation Project from the Chinese Ministry of Education
- National Science Basic Research Plan in Shaanxi Province of China [2019JQ659]
- China Postdoctoral Fund [2019M663641, 2017M613081]
- Scientific Research Project of Education Department in Shaanxi Province of China [20JY023]
- Fundamental Research Funds for the Central Universities [XJS201901, XJS201903, JBF201905, JB211908]
- CAAI-Huawei MindSpore Open Fund
The proposed deep group spatial-spectral attention fusion network is a novel classification method for PAN and MS images, which effectively combines spatial and spectral information to achieve comparable results in image interpretation through feature extraction, attention fusion, and classifier integration at pixel level.
Panchromatic (PAN) and multispectral (MS) images have coordinated and paired spatial spectral information, which can complement each other and make up for their shortcomings for image interpretation. In this article, a novel classification method called the deep group spatial-spectral attention fusion network is proposed for PAN and MS images. First, the MS image is processed by unpooling to obtain the same resolution as that of the PAN image. Second, the group spatial attention and group spectral attention modules are proposed to extract image features. The PAN and the processed MS images are regarded as the input of the two modules, respectively. Third, the features from the previous step are fused by the attention fusion module, which aims to fully fuse multilevel features, take into account both the low-level features and the high-level features, and maintain the global abstract and local detailed information of the pixels. Finally, the fusion feature is fed into the classifier and the resulting map is obtained by pixel level. Extensive experiments and analysis on four datasets show that the proposed method achieves comparable results.
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