Fuzzy graph convolutional network for hyperspectral image classification

被引:20
|
作者
Xu, Jindong [1 ]
Li, Kang [1 ,2 ]
Li, Ziyi [1 ]
Chong, Qianpeng [1 ]
Xing, Haihua [3 ]
Xing, Qianguo [4 ]
Ni, Mengying [1 ]
机构
[1] Yantai Univ, Sch Comp & Control Engn, Yantai 264005, Peoples R China
[2] Quan Cheng Lab, Jinan 250100, Peoples R China
[3] Hainan Normal Univ, Coll Informat Sci & Technol, Haikou 571158, Peoples R China
[4] Chinese Acad Sci, Yantai Inst Coastal Zone Res, Yantai 264003, Peoples R China
基金
中国国家自然科学基金;
关键词
Graph convolutional network; Hyperspectral image; Image classification; Fuzzy logic; Graph construction method;
D O I
10.1016/j.engappai.2023.107280
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
-Graph convolutional network (GCN) has attracted much attention in the field of hyperspectral image classification for its excellent feature representation and convolution on arbitrarily structured non-Euclidean data. However, most state-of-the-art methods build a graph utilize the distance measure, which makes it challenging to fully characterize the complex relationship of hyperspectral remote sensing data. Moreover, the hyperspectral image usually has uncertainty introduced by the problems of the spectral variability and noise interference. This article uses fuzzy theory to optimize the GCN and thus solve the uncertainty problem in hyperspectral images, and presents a novel fuzzy graph convolutional network (F-GCN) for hyperspectral image classification. By calculating the fuzzy similarity of samples, a robust graph is first built rather than using the traditional Euclidean distance method, which allows a better representation of the complex relationship between hyperspectral remote sensing data. Furthermore, the proposed network introduces fuzzy layers into the model to cope with the ambiguity of the hyperspectral image. Finally, the classification results for three real-world hyperspectral data sets to show its feasibility and effectiveness in hyperspectral image classification.
引用
收藏
页数:13
相关论文
共 50 条
  • [41] Adaptable Convolutional Network for Hyperspectral Image Classification
    Paoletti, Mercedes E.
    Haut, Juan M.
    REMOTE SENSING, 2021, 13 (18)
  • [42] Hypergraph convolutional network for hyperspectral image classification
    Qin Xu
    Jing Lin
    Bo Jiang
    Jinpei Liu
    Bin Luo
    Neural Computing and Applications, 2023, 35 : 21863 - 21882
  • [43] Hyperspectral image classification using feature fusion fuzzy graph broad network
    Chu, Yonghe
    Cao, Jun
    Ding, Weiping
    Huang, Jiashuang
    Ju, Hengrong
    Cao, Heling
    Liu, Guangen
    INFORMATION SCIENCES, 2025, 689
  • [44] dSPG: A New Discriminant Superpixel Graph Regularizer and Convolutional Network for Hyperspectral Image Classification
    Yu, Long
    Li, Jun
    He, Lin
    Plaza, Antonio
    Wang, Lizhe
    Tang, Zhonghui
    Zhuo, Li
    Yuan, Yuchen
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
  • [45] Multiscale Feature Search-Based Graph Convolutional Network for Hyperspectral Image Classification
    Wu, Ke
    Zhan, Yanting
    An, Ying
    Li, Suyi
    REMOTE SENSING, 2024, 16 (13)
  • [46] Feature-guided dynamic graph convolutional network for wetland hyperspectral image classification
    Li, Zhongwei
    Meng, Qiao
    Guo, Fangming
    Wang, Leiquan
    Huang, Wenhao
    Hu, Yabin
    Liang, Jian
    INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2023, 123
  • [47] Adaptive Multi-Feature Fusion Graph Convolutional Network for Hyperspectral Image Classification
    Liu, Jie
    Guan, Renxiang
    Li, Zihao
    Zhang, Jiaxuan
    Hu, Yaowen
    Wang, Xueyong
    REMOTE SENSING, 2023, 15 (23)
  • [48] Feature Fusion via Deep Residual Graph Convolutional Network for Hyperspectral Image Classification
    Chen, Rong
    Guanghui, Li
    Dai, Chenglong
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [49] Feature Fusion via Deep Residual Graph Convolutional Network for Hyperspectral Image Classification
    Chen, Rong
    Guanghui, Li
    Dai, Chenglong
    IEEE Geoscience and Remote Sensing Letters, 2022, 19
  • [50] Hyperspectral image classification based on mixed similarity graph convolutional network and pixel refinement
    Shang, Ronghua
    Zhu, Keyao
    Chang, Huidong
    Zhang, Weitong
    Feng, Jie
    Xu, Songhua
    APPLIED SOFT COMPUTING, 2025, 170