基于双池化注意力机制的高光谱图像分类算法
DOI:
作者:
作者单位:

1.重庆师范大学;2.西南大学

作者简介:

通讯作者:

中图分类号:

基金项目:

国家自然科学基金(61877051,61170192)、重庆市科委重点项目(cstc2017zdcy-zdyf0366)、重庆市教委项目(113143)、重庆市研究生教改重点项目(yjg182022)


Hyperspectral image classification algorithm based on double pool attention mechanism
Author:
Affiliation:

1.Chongqing Normal University;2.Southwest University

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为了提高高光谱图像在有限训练样本下的分类性能,提出了一种基于双池化注意力机制的高光谱图像分类网络(DPAMN)。首先,DPAMN采用三维卷积提取高光谱图像的空间和光谱浅层信息。其次,为了增强网络的特征提取能力,在DPAMN中引入了一种双池化注意力机制。最后,在网络的深层引入三维卷积密集连接模块,该模块不仅能够充分提取高光谱图像的空间和光谱特征,同时还能提高特征的判别能力。实验证明,在Indian Pines、University of Pavia、Salinas以及Houston2013数据集上能够取得95.45%、97.11%、95.30%以及93.71%的整体平均精度,与目前主流的已有先进方法相比,所提出的方法在四个数据集上均有较大提升,这表明所提出方法具有较强的泛化能力。

    Abstract:

    In order to improve the classification performance of hyperspectral images with limited training samples, a hyperspectral image classification network (DPAMN) based on double pooling attention mechanism is proposed in this paper. Firstly, DPAMN uses three-dimensional convolution to extract the spatial and spectral shallow information of hyperspectral images. Secondly, in order to enhance the feature extraction ability of the network, a double pooling attention mechanism is introduced into DPAMN. Finally, the three-dimensional convolution dense connection module is introduced into the deep layer of the network, which can not only fully extract the spatial and spectral features of hyperspectral images, but also improve the ability of feature discrimination. Experiments show that the overall average accuracy of 95.45%, 97.11%, 95.30% and 93.71% can be achieved on Indian pines, University of Pavia, Salinas and Houston 2013 data sets. Compared with the current mainstream existing advanced methods, the method proposed in this paper is greatly improved on the four data sets, which shows that the proposed method has strong generalization ability.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2022-05-05
  • 最后修改日期:2022-06-15
  • 录用日期:2022-06-16
  • 在线发布日期:
  • 出版日期:

地址:江苏南京,宁六路219号,南京信息工程大学    邮编:210044

联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2022 版权所有  技术支持:北京勤云科技发展有限公司