Hyperspectral Band Selection With Iterative Graph Autoencoder

doi:10.1109/TGRS.2023.3273776

CORC > 海洋研究所 > 中国科学院海洋研究所 > 海洋环流与波动重点实验室

	Hyperspectral Band Selection With Iterative Graph Autoencoder
	Zhou, Yuan 1; Yao, Qingren 1; Huo, Shuwei 1; Li, Xiaofeng 2,3
刊名	IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
	2023
卷号	61 页码:13
关键词	Feature extraction Iterative methods Symmetric matrices Hyperspectral imaging Convolution Correlation Task analysis Graph autoencoder (GAE) graph representation hyperspectral band selection (BS) representativeness
ISSN号	0196-2892
DOI	10.1109/TGRS.2023.3273776
通讯作者	Li, Xiaofeng(xiaofeng.li@ieee.org)
英文摘要	Hyperspectral band selection (BS) is an important task for hyperspectral image (HSI) processing, which aims to select a discriminative and low-redundant band subset. As a significant cue for BS, structure information describes the cross-band correlation, which brings the redundancy of HSI. Existing methods model structure information via manual rule-based graph construction. However, such a graph construction method fails to model complex and diverse structural relationships of HSI data. To address this problem, we propose a data-driven method, named iterative graph autoencoder for BS (IGAEBS). It adaptively captures structure information by a data-specific automatic construction process, rather than by a fixed empirical design. Specifically, we propose a new unsupervised pretext task to train graph convolution neural networks to extract HSI features. These features are used to construct a graph to represent the structural relationships among bands. To enhance the reliability of the graph, we further design an iterative graph improvement mechanism to progressively refine the structure representation. Using the derived graph, we partition the bands into several clusters and select a representative band from each cluster. During the selection process, both intracluster information and intercluster information are considered to improve the discriminativeness of band subset. Extensive experiments are conducted on three public datasets to validate the superiority of the proposed method compared to other state-of-the-art methods.
资助项目	National Key Research and Development Program of China[2020YFC1523204] ; National Natural Science Foundation of China[62171320] ; National Natural Science Foundation of China[U2006211]
WOS关键词	IMAGE
WOS研究方向	Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000996488200003
内容类型	期刊论文
源URL	[http://ir.qdio.ac.cn/handle/337002/182317]
专题	海洋研究所_海洋环流与波动重点实验室
通讯作者	Li, Xiaofeng
作者单位	1.Tianjin Univ, Sch Elect & Informat Engn, Tianjin 300072, Peoples R China 2.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Circulat & Waves, Qingdao 266071, Shandong, Peoples R China 3.Chinese Acad Sci, Ctr Ocean Mega Sci, Qingdao 266071, Peoples R China
推荐引用方式 GB/T 7714	Zhou, Yuan,Yao, Qingren,Huo, Shuwei,et al. Hyperspectral Band Selection With Iterative Graph Autoencoder[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2023,61:13.
APA	Zhou, Yuan,Yao, Qingren,Huo, Shuwei,&Li, Xiaofeng.(2023).Hyperspectral Band Selection With Iterative Graph Autoencoder.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,61,13.
MLA	Zhou, Yuan,et al."Hyperspectral Band Selection With Iterative Graph Autoencoder".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 61(2023):13.