Früher|Nächster

Hyperspectral images adaptive dimensionality reduction optimized by JM transform

  • role： First author第一作者
  • Affiliation：

    Key Laboratory of 3D Information Acquisition and Application, Ministry of Education, Capital Normal University, Beijing 100048, China

    Engineering Research Center of Spatial Information Technology, Ministry of Education, Capital Normal University, Beijing 100048, China

  • Email：xykang@cnu.edu.cn
  • Introduction：康孝岩,1989年生,男,博士研究生,研究方向为计算机视觉、机器学习、高维遥感数据处理与应用。E-mail: xykang@cnu.edu.cn;xy.muap.kxy@gmail.com
KANG Xiaoyan12,  
  • role： Corresponding author通信作者
  • Affiliation：

    Key Laboratory of 3D Information Acquisition and Application, Ministry of Education, Capital Normal University, Beijing 100048, China

    Engineering Research Center of Spatial Information Technology, Ministry of Education, Capital Normal University, Beijing 100048, China

  • Email：zhangaw98@163.com
  • Introduction：张爱武，1972年生, 女, 教授,研究方向为空间信息获取与处理、三维激光成像、高光谱成像等。E-mail: zhangaw98@163.com
ZHANG Aiwu12*,  
  • Affiliation：

    School of Mechanical Engineering & Automation, Beihang University, Beijing 100191, China

HU Shaoxing3,  
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China

XIAO Qing4,  
  • Affiliation：

    Academy of Animal and Veterinary Sciences, Qinghai University, Xining, 810016, China

CHAI Shatuo5

Resümee

Hyperspectral remote sensing images, which collect rich spectral and spatial information of observed targets, usually contain dozens to hundreds of narrow bands with wavelengths ranging from the visible light region to the near-infrared spectra. With such an abundant number of spectral features, hyperspectral images (HSI) allow us to distinguish different of objects or targets by rule and line. Unfortunately, such high-dimensionality data pose a challenge in data transmission, storage, and processing. Specifically, those HSIs with high redundancy information and strong correlation are prone to a Hughes phenomenon during the image classification process. Therefore, dimensionality reduction is necessary for targets classification. Moreover, without using prior label samples, unsupervised dimensionality reduction can effectively simplify the HSI feature space, and prevent the Hughes phenomenon in the targets classification.In this paper, the Jeffries–Matusita (JM) modified adaptive band selection (JM2ABS) method is proposed to extract proper features from HSI datasets. Generally speaking, a band that contains many information and demonstrates strong independence is a very important feature that helps unsupervised band selection methods to classify targets. The JM2ABS method considers both the information capacity and independence of HSI bands. Given the significant differences in the measurements of a band’s information capacity and its independence, we introduce the JM transform function to normalize the distributions of the information capacity and the independence of HSI data. Thus JM2ABS shows that both the information capacity and the independence are equally important in unsupervised dimensionality reduction.We also compare our proposed JM2ABS method against three typical methods, namely, the modified adaptive band selection method, the Laplacian score feature selection method, and the infinite feature selection method. By using random training samples, we perform supervised classification experiments on two kinds of HSI public datasets (linear and planar arrays). The results demonstrate that JM2ABS outperforms the other three typical methods in terms of Kappa value, overall classification accuracy, and average classification accuracy. Moreover, under a small number of bands, JM2ABS can reach a high and stable level regardless of the different datasets and different classifiers used.The proposed JM2ABS can select the proper features of HSI datasets for their classification application. The JM transform function is a kind of nonlinear distribution function that can standardize variables from different scales to the same. To demonstrate the feasibility of JM transform optimization, we set the same weight for the information content and the independence. In our future work, we will explore the similarities and differences between the information capacity and the independence in dimensionality reduction.

Schlüsselwort

remote sensing;Jeffries-Matusita transform;normalization;adaptive dimensionality reduction;unsupervised band selection;hyperspectral image

References

  1. 1.
    Bajcsy P and Groves P. 2004. Methodology for hyperspectral band selection. Photogrammetric Engineering and Remote Sensing, 70(7): 793-802
  2. 2.
    Cao X H, Wu B, Tao D C and Jiao L C. 2016. Automatic band selection using spatial-structure information and classifier-based clustering. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(9): 4352-4360
  3. 3.
    He X F, Cai D and Niyogi P. 2005. Laplacian score for feature selection//Proceedings of the 18th International Conference on Neural Information Processing Systems. Vancouver, British Columbia, Canada: MIT Press: 507-514
  4. 4.
    Ioffe S and Szegedy C. 2015. Batch normalization: accelerating deep network training by reducing internal covariate shift//Proceedings of the 32nd International Conference on Machine Learning. Lille, France: 448-456
  5. 5.
    Li S J and Qi H R. 2011. Sparse representation based band selection for hyperspectral images//Proceedings of the 18th IEEE International Conference on Image Processing. Brussels, Belgium: IEEE: 2693-2696
  6. 6.
    Liu C H, Zhao C H and Zhang L Y. 2005. A new method of hyperspectral remote sensing image dimensional reduction. Journal of Image and Graphics, 10(2): 218-222
  7. 7.
    Matusita K. 1955. Decision rules, based on the distance, for problems of fit, two samples, and estimation. The Annals of Mathematical Statistics, 26(4): 631-640
  8. 8.
    Qin F P, Zhang A W, Wang S M, Meng X G, Hu S X and Sun W D. 2015. Hyperspectral band selection based on spectral clustering and inter-class separability factor. Spectroscopy and Spectral Analysis, 35(5): 1357-1364
  9. 9.
    Richards J A. 2013. Remote Sensing Digital Image Analysis. 5th ed. Berlin, Heidelberg: Springer: 350-352
  10. 10.
    Roffo G, Melzi S and Cristani M. 2015. Infinite feature selection//IEEE International Conference on Computer Vision. Santiago, Chile: IEEE: 4202-4210
  11. 11.
    Roffo G and Melzi S. 2017. Ranking to learn: feature ranking and selection via eigenvector centrality//Appice A, Ceci M, Loglisci C, Masciari E and Raś Z, eds. New Frontiers in Mining Complex Patterns. Berlin Heidelberg: Springer: 19-35
  12. 12.
    Shukla U P and Nanda S J. 2018. A Binary Social Spider Optimization algorithm for unsupervised band selection in compressed hyperspectral images. Expert Systems with Applications, 97: 336-356
  13. 13.
    Sui C H, Tian Y, Xu Y P and Xie Y. 2015. Unsupervised band selection by integrating the overall accuracy and redundancy. IEEE Geoscience and Remote Sensing Letters, 12(1):185-189
  14. 14.
    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
  15. 15.
    Sun W W, Zhang L P, Du B, Li W Y and Lai Y M. 2015. 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
  16. 16.
    Swain P H and Davis S M. 1978. Remote Sensing: the Quantitative Approach. New York: McGraw-Hill
  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.
    Tong Q X, Zhang B and Zheng L F. 2006. Hyperspectral Remote Sensing: the Principle, Technology and Application. Beijing: Higher Education Press: 135-136
  19. 19.
    Wang L G and Wei F J. 2013. Band selection for hyperspectral imagery based on combination of genetic algorithm and ant colony algorithm. Journal of Image and Graphics, 18(2): 235-242
  20. 20.
    Yu X C, Feng W F, Yang G P and Chen W. 2013. Analysis and Application for Hyperspectral Imagery. Beijing: Science Press: 1-6
  21. 21.
    Zhang A W, Du N, Kang X Y and Guo C F. 2017. Hyperspectral adaptive band selection method through nonlinear transform and information adjacency correlation. Infrared and Laser Engineering, 46(5): 213-221
  22. 22.
    Zhang K, Hei B Q, Zhou Z and Li S Y. 2018. CNN with coefficient of variation-based dimensionality reduction for hyperspectral remote sensing images classification. Journal of Remote Sensing, 22(1): 87-96

Lesen Sie die ganze Passage

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