Früher|Nächster

NMF hyperspectral unmixing algorithm combined with spatial and spectral correlation analysis

  • role： First author第一作者
  • Affiliation：

    School of Computer and Information Engineering, Nanyang Institute of Technology, Nanyang 473004, China

  • Email：nylgyb@163.com
  • Introduction：袁博(1982—　)，男，讲师，研究方向为物联网、数字信号处理。Email：nylgyb@163.com
Bo YUAN

Resümee

The low spatial resolution of hyperspectral images always leads to the “mixed pixel” problem, where multiple objects exist in one pixel. The unmixing of mixed pixels is vital to the quantitative application of hyperspectral remote sensing. Non-negative matrix factorization (NMF) is a hot spot in hyperspectral unmixing research because of its non-negative constraints and capability to process high-dimensional data. However, NMF-based unmixing algorithms are ineffective because of universality, local minima, and other restrictions; additional specific features of hyperspectral images should be explored. Hyperspectral remote sensing images have significant correlation features, such as spatial and spectral correlation. The present study aims to improve the unmixing effect by adopting correlation features of hyperspectral remote sensing images. An NMF-based hyperspectral unmixing algorithm with spatial and spectral correlation analyses, named NMF hyperspectral unmixing algorithm based on spatial and spectral correlation (NMFSSC), is proposed to address the universality and local minima problems of NMF. The proposed method adopts the correlation features of hyperspectral data in the unmixing process as the spatial correlation constraint of building adjacent pixels. The Markov Random Field (MRF) model and spectral correlation (piecewise smoothness) are used as constraints in building adjacent bands with complexity mapping technique. In this algorithm, the spatial correlation constraint of adjacent pixels is processed as the parallel and alternate step of the standard NMF object function. The spectral correlation of the adjacent bands is built as a new inner constraint of the standard function. During each iteration of the unmixing procedure, the distribution error of endmembers can be revised by the MRF-based spatial correlation constraint. The local minima problem can be revised by the complexity mapping constraint, thus potentially improving overall unmixing precision. Actual hyperspectral data with high and low spatial correlation are adopted in the experiments. Three algorithms, namely, Minimum Volume Constrained Nonnegative Matrix Factorization (MVCNMF), Piecewise Smoothness NMF with Sparseness Constraints (PSNMFSC), and NMF with Alternating Projected Subgradients (APSNMF), are used with NMFSSC in the experiments. Results indicate that the proposed NMFSSC algorithm can improve unmixing precision, especially when dealing with high-spatial-correlation test data. The unmixing precision of NMFSSC is lower on the low-spatial-correlation data than on the high-spatial-correlation set, but the method still shows certain advantages over the three reference algorithms. Therefore, NMFSSC has a wide-ranging application scope. In summary, the proposed algorithm can increase the unmixing accuracy of most actual hyperspectral remote sensing data, especially those with high spatial correlation. The local minima and universality problems of the standard NMF can be significantly addressed by adopting the MRF model and complexity mapping technique. However, the precision of the proposed algorithm can deteriorate as the correlation feature of hyperspectral data becomes increasingly vague. If the spatial and spectral correlations of the data are low, then the precision of the algorithm can be reduced. The next step is to widen the application scope of the unmixing algorithm and stabilize its performance.

Schlüsselwort

Nonnegative Matrix Factorization(NMF);pixel un-mixing;spatial correlation;spectral correlation;Markov Random Field(MRF);complexity mapping

References

  1. 1.
    Bioucas J M and Nascimento J M P. 2008. Hyperspectral subspace identification. IEEE Transactions on Geoscience and Remote Sensing, 46(8): 2435–2445
  2. 2.
    Chen B L, Li M, Wang J X and Wu F X. 2014. Disease gene identification by using graph kernels and Markov random fields. Science China Life Sciences, 57(11): 1054–1063
  3. 3.
    Chen X W, Yu J and Sun W D. 2013. Area-correlated spectral unmixing based on Bayesian nonnegative matrix factorization. Open Journal of Applied Sciences, 3(1): 41–46
  4. 4.
    Deng H W and Clausi D A. 2004. Unsupervised image segmentation using a simple MRF model with a new implementation scheme. Pattern Recognition, 37(12): 2323–2335
  5. 5.
    Du S Q, Shi Y Q, Wang W L and Ma M. 2012. Graph regularized-based semi-supervised non-negative matrix factorization. Computer Engineering and Applications, 48(36): 194–200 (
  6. 6.
    Geng X R, Ji L Y and Sun K. 2016. Non-negative matrix factorization based unmixing for principal component transformed hyperspectral data. Frontiers of Information Technology and Electronic Engineering, 17(5): 403–412
  7. 7.
    Hoyer P O. 2004. Non-negative matrix factorization with sparseness constraints. Journal of Machine Learning Research, 5(1): 1457–1469
  8. 8.
    Huang C H. 2014. Researches on Hyperspectral Unmixing Based on Nonnegative Matrix Factorization. Xi’an: Xidian University: 36–38
  9. 9.
    Jia S and Qian Y T. 2009. Constrained nonnegative matrix factorization for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 47(1): 161–173
  10. 10.
    Jiang X Y, Sun F M and Li H J. 2016. Semi-supervised nonnegative matrix factorization based on graph regularization and sparseness constraints. Computer Science, 43(7): 77–82, 105 (
  11. 11.
    Lee D D and Seung H S. 1999. Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755): 788–791
  12. 12.
    Liu B, Liu J Z, Zhang G L, Ling Z C, Zhang J, He Z P, Yang B Y and Zou Y L. 2014. Correlation analysis and partial least square modeling to quantify typical minerals with Chang’E-3 visible and near-infrared imaging spectrometer’s ground validation data. Chinese Journal of Geochemistry, 33(1): 86–94
  13. 13.
    Liu J J, Wu Z B, Wei Z H, Xiao L and Sun L. 2012. Spatial correlation constrained sparse representation for hyperspectral image classification. Journal of Electronics and Information Technology, 34(11): 2666–2671 (
  14. 14.
    Miao L D and Qi H R. 2007. Endmember extraction from highly mixed data using minimum volume constrained nonnegative matrix factorization. IEEE Transactions on Geoscience and Remote Sensing, 45(3): 765–777
  15. 15.
    Pauca V P, Pipe J and Plemmons R J. 2006. Nonnegative matrix factorization for spectral data analysis. Linear Algebra and its Applications, 416(1): 29–47
  16. 16.
    Tang Y, Wan J W, Xu K and Wang L. 2014. Hyperspectral unmixing based on material spatial distribution characteristic. Journal of Infrared and Millimeter Waves, 33(5): 560–570 (
  17. 17.
    Wang N, Zhang L P and Du B. 2014. Minimum spectral correlation constraint algorithm based on non-negative matrix factorization for hyperspectral unmixing. Geomatics and Information Science of Wuhan University, 39(1): 22–26 (
  18. 18.
    Wu J B. 2002. D-N commutative method and its convergence. Journal on Numerical Methods and Computer Applications, 23(2): 121–130 (
  19. 19.
    Xu N, You H J, Geng X R and Cao Y G. 2016. Multi-task jointly sparse spectral unmixing method based on spectral similarity measure of hyperspectral imagery. Journal of Electronics and Information Technology, 38(11): 2701–2708 (
  20. 20.
    Xu X R, Chen L F and Zhuang J L. 2001. Genetic inverse algorithm for retrieval of component temperature of mixed pixel by multi-angle thermal infrared remote sensing data. Science in China Series D: Earth Sciences, 44(4): 363–372
  21. 21.
    You C Y, Liu W B and Chang J. 2016. Structural modal parameter identification based on complexity pursuit. Journal of Suzhou University of Science and Technology (Engineering and Technology), 29(2): 38–42 (
  22. 22.
    Zhan X L and Wu B. 2011. A method of spectral mixture analysis based on Gaussian Markov random field model. Journal of Fuzhou University (Natural Science Edition), 39(1): 60–66 (
  23. 23.
    Zhao C H, Zhu H F, Cui S L and Qi B. 2015. Multiple endmember hyperspectral sparse unmixing based on improved OMP algorithm. Journal of Harbin Institute of Technology, 22(5): 97–104
  24. 24.
    Zymnis A, Kim S J, Skaf J, Parente M and Boyd S. 2007. Hyperspectral image unmixing via alternating projected subgradients. Proceedings of 2007 Conference Record of the 41st Asilomar Conference on Signals, Systems and Computers. Pacific Grove, CA: IEEE: 598–610 [DOI: 10.1109/ACSSC.2007.4487406]

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