Research on hyperspectral image classification method based on deep learning
Author:
Affiliation:

1.Aviation Operations and Service Institute, Naval Aviation University, Yantai 264000, China;2.Coastal Defense College, Naval Aviation University, Yantai 264000, China

Clc Number:

TP18

Fund Project:

Supported by the National Natural Science Foundation of China (62005318)

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    Targeting the issue of insufficient accuracy of hyperspectral image classification methods, a hyperspectral image classification method based on Spatial-spatial transformer (SST) network is proposed. Firstly, the hyperspectral images are preprocessed into one-dimensional feature vectors. Then, the SST hyperspectral image classification network with spectral-spatial attention module and pooled residual module is designed. The overall classification accuracy of the proposed classification method on Indian Pines dataset and Pavia University dataset is 98.67% and 99.87%, respectively, which indicates that this method has high classification accuracy and provides a new scheme for hyperspectral image classification and application.

    Reference
    Related
    Cited by
Get Citation

ZHANG Bin, LIU Liang, LI Xiao-Jie, ZHOU Wei. Research on hyperspectral image classification method based on deep learning[J]. Journal of Infrared and Millimeter Waves,2023,42(6):824~832

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:January 06,2023
  • Revised:November 02,2023
  • Adopted:March 28,2023
  • Online: November 01,2023
  • Published: