Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 59, Issue 18, 1811001(2022)

Hyperspectral Image Classification Based on Convolution Neural Network with Attention Mechanism

Wenhao Chen1, Jing He1、*, and Gang Liu1,2
Author Affiliations
  • 1College of Earth Sciences, Chengdu University of Technology, Chengdu 610059, Sichuan , China
  • 2State Key Laboratory of Geohazard Prevention and Geoenvironmental Protection, Chengdu University of Technology, Chengdu 610059, Sichuan , China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (13)
    Equations (0)
    References (22)
    Cited By (6)
    Tools
    Paper Information
    Topics
    Figures & Tables(13)
    Basic structure of convolutional neural network

    Fig. 1. Basic structure of convolutional neural network

    Download full size
    Residual structure

    Fig. 2. Residual structure

    Download full size
    SE module

    Fig. 3. SE module

    Download full size
    SE-Res block

    Fig. 4. SE-Res block

    Download full size
    SE-ResNet structure

    Fig. 5. SE-ResNet structure

    Download full size
    Flase color images. (a) Indian Pines; (b) Pavia University

    Fig. 6. Flase color images. (a) Indian Pines; (b) Pavia University

    Download full size
    Overall accuracy of different reduction ratio

    Fig. 7. Overall accuracy of different reduction ratio

    Download full size
    Overall accuracy of different space sizes

    Fig. 8. Overall accuracy of different space sizes

    Download full size
    Loss and accuracy of training and validation sets of Indian Pines with different sample ratios. (a) 1∶1∶8; (b) 2∶1∶7; (c) 3∶1∶6; (d) 4∶1∶5

    Fig. 9. Loss and accuracy of training and validation sets of Indian Pines with different sample ratios. (a) 1∶1∶8; (b) 2∶1∶7; (c) 3∶1∶6; (d) 4∶1∶5

    Download full size
    Classification maps for Indian Pines. (a) Ground truth; (b) SVM; (c) 2D-CNN; (d) 3D-CNN; (e) ResNet; (f) SE-ResNet

    Fig. 10. Classification maps for Indian Pines. (a) Ground truth; (b) SVM; (c) 2D-CNN; (d) 3D-CNN; (e) ResNet; (f) SE-ResNet

    Download full size
    Classification maps for Pavia University. (a) Ground truth; (b) SVM; (c) 2D-CNN; (d) 3D-CNN; (e) ResNet; (f) SE-ResNet

    Fig. 11. Classification maps for Pavia University. (a) Ground truth; (b) SVM; (c) 2D-CNN; (d) 3D-CNN; (e) ResNet; (f) SE-ResNet

    Download full size

    • Table 1. Classification accuracy and training time of Indian Pines and Pavia University datasets with different sample ratios

      View table

      Table 1. Classification accuracy and training time of Indian Pines and Pavia University datasets with different sample ratios

      Sample ratio1∶1∶82∶1∶73∶1∶64∶1∶5
      Indian PinesOA /%95.2098.4399.4599.61
      AA /%93.2097.1499.1899.23
      Kappa /%94.5298.2099.3799.55
      Train time /s307.27524.31735.64963.75
      Pavia UniversityOA /%99.6599.8999.9399.85
      AA /%99.4499.8099.8899.64
      Kappa /%99.5399.8599.9199.80
      Train time /s673.621147.151627.133922.04

    • Table 2. Classification accuracy of Indian Pines and Pavia University datasets

      View table

      Table 2. Classification accuracy of Indian Pines and Pavia University datasets

      MethodSVM2D-CNN3D-CNNResNetSE-ResNet
      Indian PineOA /%91.4995.7698.3398.2399.45
      AA /%90.1396.2396.3798.0199.18
      Kappa /%90.2995.1698.0997.9899.37
      Pavia UniversityOA /%94.4597.3898.1598.9099.65
      AA /%92.7496.7097.1098.3199.44
      Kappa /%92.6296.5397.5598.5499.53
    Tools

    Get Citation

    Copy Citation Text

    Wenhao Chen, Jing He, Gang Liu. Hyperspectral Image Classification Based on Convolution Neural Network with Attention Mechanism[J]. Laser & Optoelectronics Progress, 2022, 59(18): 1811001

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Imaging Systems

    Received: May. 31, 2021

    Accepted: Jul. 20, 2021

    Published Online: Aug. 22, 2022

    The Author Email: Jing He (xiao00yao@163.com)

    DOI:10.3788/LOP202259.1811001

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology