Précédent|Prochain

Robust multi-feature spectral clustering for hyperspectral band selection

  • role： First author第一作者
  • Affiliation：

    Department of Geography and Spatial Information Techniques, Ningbo University, Ningbo 315211, China

  • Email：sunweiwei@nbu.edu.cn
  • Introduction：孙伟伟，1985年生，教授，研究方向为多源遥感协同智能解译与海岸带健康监测。E-mail：sunweiwei@nbu.edu.cn
SUN Weiwei1,  
  • Affiliation：

    Department of Geography and Spatial Information Techniques, Ningbo University, Ningbo 315211, China

YANG Gang1,  
  • role： Corresponding author通信作者
  • Affiliation：

    Faculty of Mathematics and Statistics, Hubei University, Wuhan 430062, China

  • Email：pengjt1982@126.com
  • Introduction：彭江涛，1982年生，教授，研究方向为高光谱遥感解译与机器学习。E-mail：pengjt1982@126.com
PENG Jiangtao2*,  
  • Affiliation：

    Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, China

MENG Xiangchao3

résumé

The Hughes problem together with strong intra-band correlations and massive data seriously hinders hyperspectral processing and further applications. Dimensionality reduction using band selection can be used to conquer the abovementioned problems and guarantee the application performance of hyperspectral data. In particular, spectral clustering is a typical method for high-dimensional hyperspectral data. This method finds clusters of all hyperspectral bands on the connected graph and selects the representatives. Unfortunately, the regular similarity measures are negatively affected by outliers or noise of hyperspectral data in measuring the similarity of different bands. They could also only represent one feature of band similarity and have respective limitations. Accordingly, the obtained similarity matrix could not represent the full information of band selection required and could not guarantee obtaining aimed bands from spectral clustering. Therefore, we propose a Robust Multifeature Spectral Clustering (RMSC) method to solve the two problems mentioned above and enhance the performance of hyperspectral band selection from spectral clustering.The RMSC combines multiple features of similarity measures for pairwise bands, namely, information entropy, band correlation, and band dissimilarity, to construct the integrated similarity matrix. It utilizes spectral information divergence to quantify the information entropy between pairwise bands. The coefficient correlation is utilized to measure the band correlations and construct the similarity matrix of band correlations. The Laplacian graph is also adopted to construct a similarity matrix and show the dissimilarity between different bands considering the inner clustering structure of all bands. The spectral angle distance matrix is constructed as well to reflect the similarity from the aspects of overall differences. The RMSC regards that each similarity matrix of all four features reflect the underlying true clustering information of all bands and has low-rank property. It formulates the estimation of combined dissimilarity matrix into a low-rank and sparse decomposition problem and utilizes the augmented Lagrangian multiplier to solve it. Thereafter, it implements the regular spectral clustering on the integrated similarity matrix and selects the representative bands from each cluster.Two hyperspectral datasets are used to design four groups of experiments and testify the performance of RMSC. Five state-of-the-art methods, namely, WaluDI, fast density-peak-based clustering, orthogonal projections based band selection, Improved Sparse Spectral Clustering (ISSC) and SC-SID, and support vector machine, are used to quantify the classification accuracy. Experimental results show that RSMC outperforms the five other band selection methods in overall classification accuracy with shorter computational time. The regularization parameter is insensitive to RMSC, and a small candidate could produce high classification accuracy.RMSC is better in selecting representative bands than current spectral clustering such as ISSC. It can also be a good choice in hyperspectral dimensionality reduction.

mots-clés

remote sensing;hyperspectral remote sensing;dimensionality reduction;band selection;spectral clustering;robust multi-feature spectral clustering

References

  1. 1.
    Chang C I, Du Q, Sun T L and Althouse M L G. 1999. A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 37(6): 2631-2641
  2. 2.
    Chang C I and Wang S. 2006. Constrained band selection for hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 44(6): 1575-1585
  3. 3.
    Du Q and Yang H. 2008. Similarity-based unsupervised band selection for hyperspectral image analysis. IEEE Geoscience and Remote Sensing Letters, 5(4): 564-568
  4. 4.
    Jia S, Tang G, Zhu J S and Li Q Q. 2016. A novel ranking-based clustering approach for hyperspectral band selection. IEEE Transactions on Geoscience and Remote Sensing, 54(1): 88-102
  5. 5.
    Lin Z C, Chen M M, Wu L Q and Ma Y. 2015. The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-rank Matrices. UILU-ENG-09-2215. Coordinated Science Laboratory, University of Illinois at Urbana-Champaign
  6. 6.
    Martínez-Usómartinez-Uso A, Pla F, Sotoca J M and GarcÍa-Sevilla P. 2007. Clustering-based hyperspectral band selection using information measures. IEEE Transactions on Geoscience and Remote Sensing, 45(12): 4158-4171
  7. 7.
    Pan B, Shi Z Z and Xu X. 2019. Analysis for the weakly Pareto optimum in multiobjective-based hyperspectral band selection. IEEE Transactions on Geoscience and Remote Sensing, 57(6): 3729-3740
  8. 8.
    Sun W W and Du Q. 2018. Graph-regularized fast and robust principal component analysis for hyperspectral band selection. IEEE Transactions on Geoscience and Remote Sensing, 56(6): 3185-3195
  9. 9.
    Sun W W, Jiang M and Li W Y. 2017. Band selection using sparse self-representation for hyperspectral imagery. Geomatics and Information Science of Wuhan University, 42(4): 441-448
  10. 10.
    Sun W W, Li W Y, Li J and Lai Y M. 2015a. Band selection using sparse nonnegative matrix factorization with the thresholded Earth's mover distance for hyperspectral imagery classification. Earth Science Informatics, 8(4): 907-918
  11. 11.
    Sun W W, Tian L, Xu Y, Zhang D F and Du Q. 2017a. Fast and robust self-representation method for hyperspectral band selection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(11): 5087-5098
  12. 12.
    Sun W W, Yang G, Du B, Zhang F F and Zhang L P. 2017b. A sparse and low-rank near-isometric linear embedding method for feature extraction in hyperspectral imagery classification. IEEE Transactions on Geoscience and Remote Sensing, 55(7): 4032-4046
  13. 13.
    Sun W W, Zhang D F, Yang G and Li W Y. 2018. Band selection for hyperspectral imagery based on weighted probabilistic archetypal analysis. Journal of Remote Sensing, 22(1): 110-118
  14. 14.
    Sun W W, Zhang L P, Du B, Li W Y and Lai Y M. 2015b. Band selection using improved sparse subspace clustering for hyperspectral imagery classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(6): 2784-2797
  15. 15.
    Sun W W, Zhang L P, Zhang L F and Lai Y M. 2016. A dissimilarity-weighted sparse self-representation method for band selection in hyperspectral imagery classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(9): 4374-4388
  16. 16.
    Tong Q X, Xue Y Q and Zhang L F. 2014. Progress in hyperspectral remote sensing science and technology in China over the past three decades. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(1): 70-91
  17. 17.
    Tong Q X, Zhang B and Zhang L F. 2016. Current progress of hyperspectral remote sensing in China. Journal of Remote Sensing, 20(5): 689-707
  18. 18.
    von Luxburg U. 2007. A tutorial on spectral clustering. Statistics and Computing, 17(4): 395-416
  19. 19.
    Wang Q, Zhang F H and Li X L. 2018. Optimal clustering framework for hyperspectral band selection. IEEE Transactions on Geoscience and Remote Sensing, 56(10): 5910-5922
  20. 20.
    Xia R K, Pan Y, Du L and Yin J. 2014. Robust multi-view spectral clustering via low-rank and sparse decomposition//Proceedings of the 28th AAAI Conference on Artificial Intelligence. Québec, Canada: AAAI: 2149-2155
  21. 21.
    Yuan Y, Lin J Z and Wang Q. 2016. Dual-clustering-based hyperspectral band selection by contextual analysis. IEEE Transactions on Geoscience and Remote Sensing, 54(3): 1431-1445
  22. 22.
    Zhang B. 2016. Advancement of hyperspectral image processing and information extraction. Journal of Remote Sensing, 20(5): 1062-1090
  23. 23.
    Zhang B, Li S S, Jia X P, Gao L R and Peng M. 2011. Adaptive Markov random field approach for classification of hyperspectral imagery. IEEE Geoscience and Remote Sensing Letters, 8(5): 973-977
  24. 24.
    Zhang L P and Li J Y. 2016. Development and prospect of sparse representation-based hyperspectral image processing and analysis. Journal of Remote Sensing, 20(5): 1091-1101
  25. 25.
    Zhang L P, Liu R and Du B. 2018. Hyperspectral remote sensing image processing by using quantum optimization algorithm. Geomatics and Information Science of Wuhan University, 43(12): 1811-1818
  26. 26.
    Zhang W Q, Li X Y, Dou Y X and Zhao L Y. 2018. A geometry-based band selection approach for hyperspectral image analysis. IEEE Transactions on Geoscience and Remote Sensing, 56(8): 4318-4333
  27. 27.
    Zhong Y F, Wang X Y, Xu Y, Wang S Y, Jia T Y, Hu X, Zhao J, Wei L F and Zhang L P. 2018. Mini-UAV-borne hyperspectral remote sensing: from observation and processing to applications. IEEE Geoscience and Remote Sensing Magazine, 6(4): 46-62

Lire l'article complet

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website