Advertisement

Journal of Real-Time Image Processing

, Volume 15, Issue 2, pp 265–277 | Cite as

Optimization of minimum volume constrained hyperspectral image unmixing on CPU–GPU heterogeneous platform

  • Zebin Wu
  • Jianjun Liu
  • Shun Ye
  • Le Sun
  • Zhihui Wei
Original Research Paper

Abstract

Hyperspectral unmixing is essential for efficient hyperspectral image processing. Nonnegative matrix factorization based on minimum volume constraint (MVC-NMF) is one of the most widely used methods for unsupervised unmixing for hyperspectral image without the pure-pixel assumption. But the model of MVC-NMF is unstable, and the traditional solution based on projected gradient algorithm (PG-MVC-NMF) converges slowly with low accuracy. In this paper, a novel parallel method is proposed for minimum volume constrained hyperspectral image unmixing on CPU–GPU Heterogeneous Platform. First, a optimized unmixing model of minimum logarithmic volume regularized NMF is introduced and solved based on the second-order approximation of function and alternating direction method of multipliers (SO-MVC-NMF). Then, the parallel algorithm for optimized MVC-NMF (PO-MVC-NMF) is proposed based on the CPU–GPU heterogeneous platform, taking advantage of the parallel processing capabilities of GPUs and logic control abilities of CPUs. Experimental results based on both simulated and real hyperspectral images indicate that the proposed algorithm is more accurate and robust than the traditional PG-MVC-NMF, and the total speedup of PO-MVC-NMF compared to PG-MVC-NMF is over 50 times.

Keywords

Hyperspectral unmixing Nonnegative matrix factorization Parallel Minimum volume constrained Optimization algorithm 

Notes

Acknowledgments

Financial support for this work, provided by the National Natural Science Foundation of China (Grants Nos. 61471199, 61101194), the Jiangsu Provincial Natural Science Foundation of China (Grant No. BK2011701), the Research Fund for the Doctoral Program of Higher Education of China (Grant No. 20113219120024), the Project of China Geological Survey (Grant No. 1212011120227), the Jiangsu Province Six Top Talents project of China (Grant No. WLW-011), and the CAST Innovation Foundation (Grant No. CAST201227), is gratefully acknowledged.

References

  1. 1.
    Liu, X., Xia, W., Wang, B., Zhang, L.: An approach based on constrained nonnegative matrix factorization to unmix hyperspectral data. IEEE Trans. Geosci. Remote Sens. 49(2), 757–772 (2011)CrossRefGoogle Scholar
  2. 2.
    Sanchez, S., Ramalho, R., Sousa, L., Plaza, A.: Real-time implementation of remotely sensed hyperspectral image unmixing on GPUs. J. Real Time Image Proc. (2012). doi: 10.1007/s11554-012-0269-2 Google Scholar
  3. 3.
    Bioucas-Dias, J.M.P., Plaza, A., Dobigeon, N., Parente, M., et al.: Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approaches. IEEE J. Sel. Topics Appl. Earth Obs Remote Sens. 5(2), 354–379 (2012)CrossRefGoogle Scholar
  4. 4.
    Nascimento, J.M.P., Bioucas-Dias, J.M.: Does independent component analysis play a role in unmixing hyperspectral data. IEEE Trans. Geosci. Remote Sens. 43(1), 175–187 (2005)CrossRefGoogle Scholar
  5. 5.
    Nascimento, J.M.P., Bioucas-Dias, J.M.: Hyperspectral unmixing algorithm via dependent component analysis. 2007 IEEE Int. Geosci. Remote Sens. Symp. 4033–4036 (2007)Google Scholar
  6. 6.
    Nascimento, J.M.P., Bioucas-Dias, J.M.: Vertex component analysis: a fast algorithm to unmix hyperspectral data. IEEE Trans. Geosci. Remote Sens. 43(4), 898–910 (2005)CrossRefGoogle Scholar
  7. 7.
    Winter, M., N-FINDR: An algorithm for fast autonomous spectral endmember determination in hyperspectral data. In: SPIE Imaging Spectrometry V, pp. 266–275. SPLE Pub, San Diego, Washington (1999)Google Scholar
  8. 8.
    Chang, C.I., Wu, C.C., Liu, W., Ouyang, Y.C.: A new growing method for simplex-based endmember extraction algorithm. IEEE Trans. Geosci. Remote Sens. 44(10), 2804–2819 (2006)CrossRefGoogle Scholar
  9. 9.
    Chi, C.Y., Chan, T.H., Ma, W.K.: A convex analysis based minimum-volume enclosing simplex algorithm for hyperspectral unmixing. In: IEEE International Conference in Acoustics, Speech and Signal Porcessing, ICASSP’2009. Taiwan (2009)Google Scholar
  10. 10.
    Miao, L., Qi, H.: Endmember extraction from highly mixed data using minimum volume constrained nonnegative matrix factorization. IEEE Trans. Geosci. Remote Sens. 45(3), 765–777 (2007)CrossRefGoogle Scholar
  11. 11.
    Yu, Y., Guo, S., Sun, W.: Minimum distance constrained non-negative matrix factorization for the endmember extraction of hyperspectral images. Proc. SPIE 6790, 679015 (2007)CrossRefGoogle Scholar
  12. 12.
    Pauca, V.P., Piper, J., Plemmons, R.J.: Nonnegative matrix factorization for spectral data analysis. Lin. Alg. Appl. 416, 29–47 (2006)MathSciNetCrossRefMATHGoogle Scholar
  13. 13.
    Jia, S., Qian, Y.: Constrained nonnegative matrix factorization for hyperspectral unmixing. IEEE Trans. Geosci. Remote Sens. 47(1), 161–173 (2009)CrossRefGoogle Scholar
  14. 14.
    Yang, Z., Zhou, G., Xie, S., Ding, S., Yang, J., Zhang, J.: Blind spectral unmixing based on sparse nonnegative matrix factorization. IEEE Trans. Image Process. 25(4), 1112–1125 (2011)MathSciNetCrossRefMATHGoogle Scholar
  15. 15.
    Qian, Y., Jia, S., Zhou, J., Robles-Kelly, A.: Hyperspectral unmixing via l 1/2 sparsity-constrained nonnegative matrix factorization. IEEE Trans. Geosci. Remote Sens. 49(11), 1–16 (2011)CrossRefGoogle Scholar
  16. 16.
    Christophe, E., Michel, J., Inglada, J.: Remote sensing processing: from multicore to gpu. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 4(3), 643–652 (2011)CrossRefGoogle Scholar
  17. 17.
    Lee, C.A., Gasster, S.D., Plaza, A., et al.: Recent developments in high performance computing for remote sensing: a review. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 4(3), 508–527 (2011)CrossRefGoogle Scholar
  18. 18.
    Plaza, A., Du, Q., Chang, Y.-L., King, R.L.: High performance computing for hyperspectral remote sensing. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 4(3), 528–544 (2011)CrossRefGoogle Scholar
  19. 19.
    Sanchez, S., Ramalho, R., Sousa, L., Plaza, A.: Real-time implementation of remotely sensed hyperspectral image unmixing on GPUs. J. Real Time Image Proc. (2012). doi: 10.1007/s11554-012-0269-2 Google Scholar
  20. 20.
    Wu, X., Huang, B., Plaza, A., Li, Y., Wu, C.: Real-time implementation of the pixel purity index algorithm for endmember identification on GPUs. IEEE Geosci. Remote Sens. Lett. 11(5), 955–959 (2013)CrossRefGoogle Scholar
  21. 21.
    Plaza, A., Plaza, J., Sanchez, S.: Parallel implementation of endmember extraction algorithms using NVIDIA graphical processing units. 2009 IEEE Int. Geosci. Remote Sens. Symp. (IGARSS 2009) 5, 208–211 (2009)Google Scholar
  22. 22.
    Luo, W.: Parallel implementation of N-FINDR algorithm for hyperspectral imagery on hybrid multiple-core CPU and GPU parallel platform. Proc. SPIE 8006, 80060A–80066A (2011)CrossRefGoogle Scholar
  23. 23.
    Bernabe, S., Sanchez, S., Plaza, A., Lopez, S., Benediktsson, J.A., Sarmiento, R.: Hyperspectral unmixing on GPUs and multi-core processors: a comparison. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 6(3), 1386–1398 (2013)CrossRefGoogle Scholar
  24. 24.
    Barberis, A., Danese, G., Leporati, F., Plaza, A., Torti, E.: Real-time implementation of the vertex component analysis algorithm on GPUs. IEEE Geosci. Remote Sens. Lett. 10(2), 251–255 (2013)CrossRefGoogle Scholar
  25. 25.
    Tarabalka, Y., Haavardsholm, T.V., Kasen, I., Skauli, T.: Real-time anolmaly detection in hyperspectral images using multivariate normal mixture models and GPU processing. J. Real Time Image Proc. 4(3), 287–300 (2009)CrossRefGoogle Scholar
  26. 26.
    Heinz, D.C.: Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 39(3), 529–545 (2001)CrossRefGoogle Scholar
  27. 27.
    Lin, C.J.: Projected gradient methods for nonnegative matrix factorization. Neural Comput. 19(10), 2756–2779 (2007)MathSciNetCrossRefMATHGoogle Scholar
  28. 28.
    Zhang, Y.: An alternating direction algorithm for nonnegative matrix factorization. Rice Technical Report (2010)Google Scholar
  29. 29.
    NVIDIA Developer Zone. cuBLAS User Guide. http://www.docs.nvidia.com/cuda/cublas/index.html (2013)
  30. 30.
    Clark, R.N., Swayze, G.A., Gallagher, A.J., King, T.V., Calvin, W.M.: The US Geological Survey, digital spectral library: version 1: 0.2 to 3.0 microns. US Geol. Surv. Open File Rep. 93(592), 1340 (1993)Google Scholar
  31. 31.
    Dias, J.M.B., Nascimento, J.M.P.: Hyperspectral subspace identification. IEEE Trans. Geosci. Remote Sens. 46(8), 2435–2445 (2008)CrossRefGoogle Scholar
  32. 32.
    EM Photonics: CULA Programmer’s Guide. http://www.culatools.com/cula_dense_programmers_guide/ (2014)
  33. 33.
    Plaza, A.: Special issue on architectures and techniques for real-time processing of remotely sensed images. J. Real Time Image Process. 4, 191–193 (2009)CrossRefGoogle Scholar
  34. 34.
    Nascimento, J.M.P., Bioucas-Dias, J.M., Rodriguez Alves, J.M., Silva, V., Plaza, A.: Parallel hyperspectral unmixing on GPUs. IEEE Geosci. Remote Sens. Lett. 11(3), 666–670 (2014)CrossRefGoogle Scholar
  35. 35.
    Bernabe, S., Sanchez, S., Plaza, A., Lopez, S., Benediktsson, J.A., Sarmiento, R.: Hyperspectral unmixing on GPUs and multi-core processors: a comparison. IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens. 6(3), 1386–1398 (2013)CrossRefGoogle Scholar
  36. 36.
    Bernabe, S., Lopez, S., Plaza, A., Sarmiento, R.: GPU implementation of an automatic target detection and classification algorithm for hyperspectral image analysis. IEEE Geosci. Remote Sens. Lett. 10(2), 221–225 (2013)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Zebin Wu
    • 1
    • 2
    • 3
  • Jianjun Liu
    • 1
  • Shun Ye
    • 1
  • Le Sun
    • 1
  • Zhihui Wei
    • 1
    • 3
  1. 1.School of Computer Science and EngineeringNanjing University of Science and TechnologyNanjingChina
  2. 2.Lianyungang Research Institute of NUSTLianyungangChina
  3. 3.Jiangsu Key Lab of Spectral Imaging and Intelligent SensingNanjingChina

Personalised recommendations