基于信息熵的加权块稀疏子空间聚类算法
作者:
作者单位:

1.广东工业大学应用数学学院,广州 510006;2.广东工业大学计算机学院,广州 510006;3.南京大学计算机软件新技术国家重点实验室,南京 210093

作者简介:

通讯作者:

基金项目:

广东省基础与应用基础研究基金(2020A1515011409,2020A1515010408)资助项目;广东省信息物理融合系统重点实验室基金(2016B030301008)资助项目;南京大学计算机软件新技术国家重点实验室基金(KFKT2020B17)资助项目。


Weighted Block Sparse Subspace Clustering Algorithm Based on Information Entropy
Author:
Affiliation:

1.School of Applied Mathematics, Guangdong University of Technology, Guangzhou 510006, China;2.School of Computers, Guangdong University of Technology, Guangzhou 510006, China;3.State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210093, China

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
    摘要:

    稀疏子空间聚类(Sparse subspace clustering, SSC)算法在处理高光谱遥感影像时,地物的划分精度较低,为了提高地物划分精度,本文提出了一种基于信息熵的加权块稀疏子空间聚类算法(Weighted block sparse subspace clustering algorithm based on information entropy, EBSSC)。信息熵权重与块对角约束的引入,可以在仿真实验前获得两像素属于同一类别的先验概率,从而正向干预模型求解出的解趋于块对角结构的最优近似解,使模型获得对抗噪声和异常值的性能,从而提高模型分类的判别能力,以获得更好的地物划分精度。在3个经典高光谱遥感数据集上的实验结果表明,本文算法聚类高光谱影像的效果优于现有的几个经典流行的子空间聚类算法。

    Abstract:

    When the sparse subspace clustering algorithm processes hyperspectral remote sensing images, the classification accuracy of features is low. In order to improve the accuracy of feature classification, this paper proposes a weighted block sparse subspace clustering algorithm based on information entropy (EBSSC). The introduction of information entropy weight and block diagonal constraint can obtain the prior probability that two pixels belong to the same category before the simulation experiment, so that the solution solved by the positive intervention model becomes the optimal approximate solution of the block diagonal structure, making the model obtain the performance against noise and outliers, thereby improving the discriminative ability of model classification to obtain better classification accuracy of ground features. Experimental results on three classical hyperspectral remote sensing data sets show that the clustering effect of hyperspectral image in this paper is better than that of several existing classical and popular subspace clustering algorithms.

    表 4 Pavia Centre图像总体聚类精度OA、Kappa系数、用户精度和制图精度Table 4 Overall clustering accuracy, Kappa coefficient, User’s accuracy and Producer’s accuracy of Pavia Centre image
    表 5 Salinas-A图像总体聚类精度OA、Kappa系数、用户精度和制图精度Table 5 Overall clustering accuracy, Kappa coefficient, User’s accuracy and Producer’s accuracy of Salinas-A image database
    表 3 Pavia大学图像总体聚类精度OA、Kappa系数、用户精度和制图精度Table 3 Overall clustering accuracy, Kappa coefficient, User’s accuracy and Producer’s accuracy of Pavia University image
    图1 GSSC算法与EBSSC算法在3个经典遥感影像上的聚类结果Fig.1 Clustering results of GSSC and EBSSC algorithms on three classic remote sensing images
    图2 Pavia University影像地面图与7种算法聚类结果图Fig.2 Ground truth image and clustering results of seven algorithms on Pavia University dataset
    图3 Pavia Centre影像地面图与7种算法聚类结果图Fig.3 Ground truth image and clustering results of seven algorithms on Pavia Centre dataset
    图4 Salinas-A影像地面图与7种算法聚类结果图Fig.4 Ground truth image and clustering results of seven algorithms on Salinas-A
    参考文献
    相似文献
    引证文献
引用本文

龙咏红,邓秀勤,王卓薇,刘玉兰.基于信息熵的加权块稀疏子空间聚类算法[J].数据采集与处理,2021,36(3):544-555

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
历史
  • 收稿日期:2020-05-30
  • 最后修改日期:2020-06-06
  • 录用日期:
  • 在线发布日期: 2021-06-16