Advertisement

Comparative Analysis of Unmixing Algorithms Using Synthetic Hyperspectral Data

  • Menna M. ElkholyEmail author
  • Marwa MostafaEmail author
  • Hala M. EbeidEmail author
  • Mohamed F. TolbaEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 921)

Abstract

Hyperspectral imaging (HS) records hundreds of continuous bands for each pixel in an image. Due to coarse spatial resolution of HS, and multiple scattering, the spectral measured by the hyperspectral cameras (HSCs) are mixtures of spectra of materials in each pixel. Thus, at each pixel, a spectral unmixing process is required to utilize an accurate estimation of the number of endmembers, their signatures and their abundances fraction. In this paper, we present a large-scale comparison of endmember extraction algorithms. The algorithms explored Vertex Component Analysis algorithm (VCA), Minimum Volume Simplex Analysis (MVSA), N-FINDR, Alternating Volume Maximization (AVMAX), Pixel Purity Index (PPI), Simplex Identification Via Split Augmented Lagrange (SISAL). Three categories of experiments were carried out; accuracy assessment, robustness to the noise, and execution time. The performance of algorithms was evaluated using two different metrics (MSE and SAD). We use simulated hyperspectral dataset sampled from USGS library - The experimental results show that MVSA and SISAL demonstrate robust performance to the changes in the size of the scene. PPI had the least performance compared with other algorithms. AVMAX and VCA have almost identical performance.

Keywords

Spectral unmixing Hyperspectral images Endmember extraction Simulated dataset 

References

  1. 1.
    Bioucas-Dias, J.M., Plaza, A., Dobigeon, N., Parente, M., Gader, P.: Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approaches. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 5(2), 354–379 (2012)CrossRefGoogle Scholar
  2. 2.
    Yu, J., Chen, D., Lin, Y.: Comparison of linear and nonlinear spectral unmixing approaches: a case study with multispectral TM imagery. Int. J. Remote Sens. 38(3), 773–795 (2016)CrossRefGoogle Scholar
  3. 3.
    Li, J., Bioucas-Dias, J.M.: Minimum volume simplex analysis: a fast algorithm to unmix hyperspectral data. In: IEEE International Geoscience and Remote Sensing Symposium, vol. 3, p. III-250 (2008)Google Scholar
  4. 4.
    Li, J., Agathos, A., Zaharie, D., Bioucas Dias, J.M., Plaza, A.: Minimum volume simplex analysis: a fast algorithm for linear hyperspectral unmixing. IEEE Trans. Geosci. Remote Sens. 53(9), 5067–5082 (2015)CrossRefGoogle Scholar
  5. 5.
    Chang, C., Wu, C., Liu, W., Ouyang, Y.: A new growing method for simplex-based endmember extraction algorithm. IEEE Trans. Geosci. Remote Sens. 44(10), 2804–2819 (2006)CrossRefGoogle Scholar
  6. 6.
    Bioucas-Dias, J.M.: A variable splitting augmented Lagrangian approach to linear spectral unmixing. In: IEEE GRSS Workshop on Hyperspectral Image and Signal Processing-WHISPERS, pp. 1–4 (2009)Google Scholar
  7. 7.
    Wang, F., Chi, C., Chan, T., Wang, Y.: Nonnegative least-correlated component analysis for separation of dependent sources by volume maximization. IEEE Trans. Pattern Anal. Mach. Intell. 32(5), 875–888 (2010)CrossRefGoogle Scholar
  8. 8.
    Zymnis, A., Kim, S., Skaf, J.: Hyperspectral image unmixing via alternating projected sub gradients. In: Record of the Forty-First IEEE Asilomar Conference on In Signals, Systems and Computers, pp. 1164–1168 (2007)Google Scholar
  9. 9.
    Nascimento, J.M.P., Bioucas-Dias, J.M.: Hyperspectral unmixing algorithm via dependent component analysis. In: IEEE International in Geoscience and Remote Sensing Symposium, pp. 4033–4036 (2007)Google Scholar
  10. 10.
    Ozkan, S., Kaya, B., Bozdagi Akar, G.: EndNet: sparse autoencoder network for endmember extraction and hyperspectral unmixing. IEEE Trans. Geosci. Remote Sens. 8(99), 1–5 (2018)Google Scholar
  11. 11.
    Nascimento, J., Dias, J.: Vertex component analysis: a fast algorithm to unmix hyperspectral data. IEEE Trans. Geosci. Remote Sens. 43(4), 898–910 (2005)CrossRefGoogle Scholar
  12. 12.
    Winter, M.E.: N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral data. In: SPIE Conference on Imaging Spectrometry, pp. 266–275 (1999)Google Scholar
  13. 13.
    Ambikapathi, A., Chan, T., Ma, W., Chi, C.: A robust alternating volume maximization algorithm for endmember extraction in hyperspectral images. In: 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (2010)Google Scholar
  14. 14.
    Wu, h., Chaudhry, F., Liu, W.: Pixel purity index-based algorithms for endmember extraction from hyperspectral imagery. In: Recent Advances in Hyperspectral Signal and Image Processing, pp. 30–62 (2006)Google Scholar
  15. 15.
    Clark, R.N., Swayze, G.A., Gallagher, A.J., Calvin, W.M.: The U.S. Geological Survey, Digital Spectral Library: Version 1 (0.2 to 3.0um) (1993)Google Scholar
  16. 16.
    Minka, T.P.: Estimating a Dirichlet distribution. Technical report (2000)Google Scholar
  17. 17.
    Yang, C., Everitt, J., Bradford, J.: Yield estimation from hyperspectral imagery using Spectral Angle Mapper (SAM). Trans. ASABE 51(2), 729–737 (2008)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Faculty of Computer and Information SciencesAin Shams UniversityCairoEgypt
  2. 2.Data Reception, Analysis and Receiving Station AffairsNational Authority for Remote Sensing and Space ScienceCairoEgypt

Personalised recommendations