Hyperspectral image unmixing algorithm based on endmember-constrained nonnegative matrix factorization

Abstract

The objective function of classical nonnegative matrix factorization (NMF) is non-convexity, which affects the obtaining of optimal solutions. In this paper, we proposed a NMF algorithm, and this algorithm was based on the constraint of endmember spectral correlation minimization and endmember spectral difference maximization. The size of endmember spectral overall-correlation was measured by the correlation function, and correlation function was defined as the sum of the absolute values of every two correlation coefficient between the spectra. In the difference constraint of the endmember spectra, the mutation of matrix trace was slowed down by introducing the natural logarithm function. Combining the image decomposition error with the influences of endmember spectra, in the objective function the projection gradient was used to achieve NMF. The effectiveness of algorithm was verified by the simulated hyperspectral images and real hyperspectral images.

Keywords

hyperspectral image / unmixing / nonnegative matrix factorization (NMF) / correlation / logarithm function

References

[1] Thouvenin P A, Dobigeon N, Tourneret J Y. Hyperspectral unmixing with spectral variability using a perturbed linear mixing model. IEEE Transactions on Signal Processing, 2016, 64(2): 525–538

[2] Heylen R, Scheunders P. A multilinear mixing model for nonlinear spectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(1): 240–251

[3] Zheng C Y, Li H, Wang Q, Chen C L P. Reweighted sparse regression for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(1):479–488

[4] Altmann Y, Pereyra M, Bioucas-Dias J. Collaborative sparse regression using spatially correlated supports—application to hyperspectral unmixing. IEEE Transactions on Image Processing, 2015, 24(12): 5800–5811

[5] Guillamet D, Vitrià J, Schiele B. Introducing a weighted non-negative matrix factorization for image classification. Pattern Recognition Letters, 2003, 24(14): 2447–2454

[6] Pauca V P, Piper J, Plemmons R J. Nonnegative matrix factorization for spectral data analysis. Linear Algebra and Its Applications, 2006, 416(1): 29–47

[7] Miao L, Qi H. Endmember extraction from highly mixed data using minimum volume constrained nonnegative matrix factorization. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(3): 765–777

[8] Hoyer P O. Non-negative matrix factorization with sparseness constraints. Journal of Machine Learning Research, 2004, 5(1): 1457–1469

[9] Lu X, Wu H, Yuan Y. Double constrained NMF for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(5): 2746–2758

[10] Luo W F, Zhong L, Zhang B, Gao L R. Independent component analysis for spectral unmixing in hyperspectral remote sensing image. Spectroscopy and Spectral Analysis, 2010, 30(6): 1628–1633 (in Chinese)

[11] Wu B, Zhao Y, Zhou X. Unmixing mixture pixels of hyperspectral imagery using endmember constrained nonnegative matrix factorization. Computer Engineering, 2008, 34(22): 229–231

[12] Chang C, Du Q. Estimation of number of spectrally distinct signal sources in hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(3): 608–619

[13] Heinz D C, Chang C. Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(3): 529–545

[14] Gillis N, Glineur F. Using underapproximations for sparse nonnegative matrix factorization. Pattern Recognition, 2010, 43(4): 1676–1687

[15] Clark R N, Swayze G A. Evolution in imaging spectroscopy analysis and sensor signal-to-noise: an examination of how far we have come. In: Proceedings of The 6th Annual JPL Airborne Earth Science Workshop, 1996

Acknowledgements

This work was supported by the National Natural Science Foundation of China (Grant No. 61275010) and the Scientific Research Fund of Heilongjiang Provincial Education Department (No. 12541734).

RIGHTS & PERMISSIONS

2016 Higher Education Press and Springer-Verlag Berlin Heidelberg