Hyperspectral Rock Classification Method Based on Spatial-Spectral Multidimensional Feature Fusion

被引:0
|
作者
Cao, Shixian [1 ]
Wu, Wenyuan [1 ,2 ]
Wang, Xinyu [1 ]
Xie, Shanjuan [1 ,2 ]
机构
[1] Hangzhou Normal Univ, Inst Remote Sensing & Earth Sci, Sch Informat Sci & Technol, Hangzhou 311121, Peoples R China
[2] Hangzhou Normal Univ, Zhejiang Prov Key Lab Urban Wetlands & Reg Change, Hangzhou 311121, Peoples R China
基金
中国国家自然科学基金;
关键词
hyperspectral imaging; rock image classification; convolutional neural network; recurrent neural network; space spectral fusion;
D O I
10.3390/min14090923
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
The issues of the same material with different spectra and the same spectra for different materials pose challenges in hyperspectral rock classification. This paper proposes a multidimensional feature network based on 2-D convolutional neural networks (2-D CNNs) and recurrent neural networks (RNNs) for achieving deep combined extraction and fusion of spatial information, such as the rock shape and texture, with spectral information. Experiments are conducted on a hyperspectral rock image dataset obtained by scanning 81 common igneous and metamorphic rock samples using the HySpex hyperspectral sensor imaging system to validate the effectiveness of the proposed network model. The results show that the model achieved an overall classification accuracy of 97.925% and an average classification accuracy of 97.956% on this dataset, surpassing the performances of existing models in the field of rock classification.
引用
收藏
页数:18
相关论文
共 50 条
  • [21] A capsule network for hyperspectral image classification employing spatial-spectral feature
    Du P.
    Zhang W.
    Zhang P.
    Lin C.
    Guo S.
    Hu Z.
    Cehui Xuebao/Acta Geodaetica et Cartographica Sinica, 2023, 52 (07): : 1090 - 1104
  • [22] Multiscale Spatial-Spectral Feature Extraction Network for Hyperspectral Image Classification
    Ye, Zhen
    Li, Cuiling
    Liu, Qingxin
    Bai, Lin
    Fowler, James E.
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 : 4640 - 4652
  • [23] Hyperspectral Image Spectral-Spatial Classification Method Based on Deep Adaptive Feature Fusion
    Mu, Caihong
    Liu, Yijin
    Liu, Yi
    REMOTE SENSING, 2021, 13 (04) : 1 - 21
  • [24] SPATIAL-SPECTRAL FEATURE EXTRACTION ON HYPERSPECTRAL IMAGERY
    Kaufman, J.
    Weinheimer, J. J.
    Celenk, M.
    2014 6TH WORKSHOP ON HYPERSPECTRAL IMAGE AND SIGNAL PROCESSING: EVOLUTION IN REMOTE SENSING (WHISPERS), 2014,
  • [25] Matrix-Based Discriminant Subspace Ensemble for Hyperspectral Image Spatial-Spectral Feature Fusion
    Hang, Renlong
    Liu, Qingshan
    Song, Huihui
    Sun, Yubao
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (02): : 783 - 794
  • [26] Assessment of Spatial-Spectral Feature-Level Fusion for Hyperspectral Target Detection
    Kaufman, Jason R.
    Eismann, Michael T.
    Celenk, Mehmet
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2015, 8 (06) : 2534 - 2544
  • [27] Feature Fusion Classification for Optical Image and SAR Image Based on Spatial-spectral Attention
    Jiang, Wen
    Pan, Jie
    Zhu, Jinbiao
    Yue, Xijuan
    JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 2023, 45 (03) : 987 - 995
  • [28] Three-Dimensional Spatial-Spectral Filtering Based Feature Extraction for Hyperspectral Image Classification
    Akyurek, Hasan Ali
    Kocer, Baris
    ADVANCES IN ELECTRICAL AND COMPUTER ENGINEERING, 2017, 17 (02) : 95 - 102
  • [29] Semisupervised classification for hyperspectral image based on spatial-spectral clustering
    Wang, Liguo
    Yang, Yueshuang
    Liu, Danfeng
    JOURNAL OF APPLIED REMOTE SENSING, 2015, 9
  • [30] Feature Reduction Based on the Fusion of Spectral and Spatial Transformation for Hyperspectral Image Classification
    Hossain, Md Moazzem
    Hossain, Md Ali
    Al Mamun, Md
    Hossain, Md Mamun
    2020 IEEE REGION 10 SYMPOSIUM (TENSYMP) - TECHNOLOGY FOR IMPACTFUL SUSTAINABLE DEVELOPMENT, 2020, : 150 - 153