Algorithm based on band statistical information weighted K-means for hyperspectral image classification

被引：0
|
作者：
Li Y. [1 ]
Zhen C. [1 ]
Shi X. [1 ]
Zhu L. [2 ]
机构：
[1] School of Geomatics, Liaoning Technical University, Fuxin
[2] Huludao Hongyue Group CO., Ltd., Huludao
来源：
Kongzhi yu Juece/Control and Decision | 2021年 / 36卷 / 05期
关键词：
Classification; Entropy information; Feature weighting; Hyperspectral image; K-means; Statistical information;
D O I：
10.13195/j.kzyjc.2019.1516
中图分类号：
学科分类号：
摘要：
Aiming at the problem of how to use band information reasonably in the hyperspectral image classification, this paper proposes a hyperspectral image classification algorithm based on band statistical information weighted K-means clustering. The algorithm considers not only the quantity of information contained in each band and the correlation between bands but also the importance of each band to different clusters. The band weight is determined by the statistics of information and correlation functions. The statistics of information function is defined according to the entropy, standard deviation and mean value of the band image. The correlation function is defined according to the mutual information of adjacent band images. In order to express the importance of each band to different clusters, the band-category weight is introduced, and its entropy information measurement is defined. The above two types of weights are embedded into the K-means objective function. The final classification result can be obtained by minimizing the objective function. Classification experiments are conducted on Salinas and Pavia Centre hyperspectral images using the proposed algorithm, the traditional K-means algorithm, the PCA + K-means algorithm and the subspace band selection + K-means algorithm, respectively. The results demonstrate that the proposed algorithm is higher than the other three algorithms on overall accuracy and Kappa. It shows that the proposed algorithm can effectively improve the performance of hyperspectral image classification. Copyright ©2021 Control and Decision.
引用
收藏
页码：1119 / 1126
页数：7
相关论文
共 20 条
  • [1] Guo X, Huang X, Zhang L E, Et al., Support tensor machines for classification of hyperspectral remote sensing imagery, IEEE Transactions on Geoscience and Remote Sensing, 54, 6, pp. 3248-3264, (2016)
  • [2] Qiu C, Liao G, Tang H, Et al., Derivative parameters of hyperspectral NDVI and its application in the inversion of rapeseed leaf area index, Applied Sciences, 8, 8, (2018)
  • [3] Mathieu M, Roy R, Launeau P, Et al., Alteration mapping on drill cores using a HySpex SWIR-320m hyperspectral camera: Application to the exploration of an unconformity-related uranium deposit (Saskatchewan, Canada), Journal of Geochemical Exploration, 172, pp. 71-88, (2017)
  • [4] Xu Q, Ma Y, Jiang Q, Et al., Estimation of rice leaf water content based on hyperspectral remote sensing, Remote Sensing Information, 33, 5, pp. 1-8, (2018)
  • [5] Tang B, Liu Z, Xiao X Y, Et al., Spectral-spatial hyperspectral classification based on multi-center SAM and MRF, Optical Review, 22, 6, pp. 911-918, (2015)
  • [6] Liao W Z, Goossens B, Aelterman J, Et al., Hyperspectral image deblurring with PCA and total variation, 2013 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), pp. 1-4, (2013)
  • [7] Fang Y, Li H, Ma Y, Et al., Dimensionality reduction of hyperspectral images based on robust spatial information using locally linear embedding, IEEE Geoscience and Remote Sensing Letters, 11, 10, pp. 1712-1716, (2014)
  • [8] Ziemann A K, Messinger D W, Wenger P S., An adaptive k-nearest neighbor graph building technique with applications to hyperspectral imagery, 2014 IEEE Western New York Image and Signal Processing Workshop (WNYISPW), pp. 32-36, (2014)
  • [9] Yang G, Sun W W, Zhang D F., Separable nonnegative matrix factorization based band selection for hyperspectral imagery, Geomatics and Information Science of Wuhan University, 44, 5, pp. 737-744, (2019)
  • [10] Zhai Y G, Zhang L F, Wang N, Et al., A modified locality-preserving projection approach for hyperspectral image classification, IEEE Geoscience and Remote Sensing Letters, 13, 8, pp. 1059-1063, (2016)
12