• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Yang, Pan (Yang, Pan.) | Tong, Lei (Tong, Lei.) | Qian, Bin (Qian, Bin.) | Gao, Zheng (Gao, Zheng.) | Yu, Jing (Yu, Jing.) | Xiao, Chuangbai (Xiao, Chuangbai.)

收录:

EI Scopus SCIE

摘要:

Convolutional neural networks (CNN) have achieved excellent performance for the hyperspectral image (HSI) classification problem due to better extracting spectral and spatial information. However, CNN can only perform convolution calculations on Euclidean datasets. To solve this problem, recently, the graph convolutional neural network (GCN) is proposed, which can be applied to the semisupervised HSI classification problem. However, the GCN is a direct push learning method, which requires all nodes to participate in the training process to get the node embedding. This may bring great computational cost for the hyperspectral data with a large number of pixels. Therefore, in this article, we propose an inductive learning method to solve the problem. It constructs the graph by sampling and aggregating (GraphSAGE) feature from a node's local neighborhood. This could greatly reduce the space complexity. Moreover, to enhance the classification performance, we also construct the graph using spectral and spatial information (spectra-spatial GraphSAGE). Experiments on several hyperspectral image datasets show that the proposed method can achieve better classification performance compared with state-of-the-art HSI classification methods.

关键词:

spectral and spatial inductive learning method hyperspectral image classification Aggregates Hyperspectral imaging Convolution Feature extraction Learning systems Support vector machines GraphSAGE Training

作者机构:

  • [ 1 ] [Yang, Pan]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 2 ] [Tong, Lei]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 3 ] [Gao, Zheng]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 4 ] [Xiao, Chuangbai]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 5 ] [Yang, Pan]Minist Educ, Engn Res Ctr Intelligent Percept & Autonomous Con, Beijing 100124, Peoples R China
  • [ 6 ] [Tong, Lei]Minist Educ, Engn Res Ctr Intelligent Percept & Autonomous Con, Beijing 100124, Peoples R China
  • [ 7 ] [Qian, Bin]Minist Publ Secur, Traff Management Res Inst, Wuxi 214151, Jiangsu, Peoples R China
  • [ 8 ] [Yu, Jing]Minist Publ Secur, Traff Management Res Inst, Wuxi 214151, Jiangsu, Peoples R China

通讯作者信息:

  • [Tong, Lei]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China

查看成果更多字段

相关关键词:

相关文章:

来源 :

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING

ISSN: 1939-1404

年份: 2021

卷: 14

页码: 791-800

5 . 5 0 0

JCR@2022

ESI学科: GEOSCIENCES;

ESI高被引阀值:64

JCR分区:1

被引次数:

WoS核心集被引频次: 2

SCOPUS被引频次: 35

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 1

归属院系:

在线人数/总访问数:492/4956686
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司