Unmixing of Hyperspectral Images with Pure Prior Spectral Pixels

Abir Zidi, Julien Marot, Klaus Spinnler, Salah Bourennane

2015

Abstract

In the literature, there are several methods for multilinear source separation. We find the most popular ones such as nonnegative matrix factorization (NMF), canonical polyadic decomposition (PARAFAC). In this paper, we solved the problem of the hyperspectral imaging with NMF algorithm. We based on the physical property to improve and to relate the output endmembers spectra to the physical properties of the input data. To achieve this,we added a regularization which enforces the closeness of the output endmembers to automatically selected reference spectra. Afterwards we accounted for these reference spectra and their locations in the initialization matrices. To illustrate our methods, we used self-acquired hyperspectral images (HSIs). The first scene is compound of leaves at the macroscopic level. In a controlled environment, we extract the spectra of three pigments. The second scene is acquired from an airplane: We distinguish between vegetation, water, and soil.

References

  1. H. Kim and K. Park, ”Non-negative Matrix Factorization Based on Alternating Non-negativity Constrained Least Squares and Active Set Method”, SIAM J.'l Matrix Analysis and Applications, vol. 30(2), pp. 713- 730, 2008.
  2. A. Cichocki, S. Amari, R. Zduneck, and A.H. Phan, ”Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation”, Wiley- Blackwell, 2009.
  3. W. Chen and M. Guillaume, ”HALS-based NMF with flexible constraints for hyperspectral unmixing”, EURASIP Journal on Advances in Signal Processing, vol. 2012(54), March 2012.
  4. N. Dobigeon and C. Fevotte, ”Robust nonnegative matrix factorization for nonlinear unmixing of hyperspectral images,” IEEE WHISPERS, Gainesville, FL, June 2013.
  5. Ma et al, ”A signal processing perspective on hyperspectral unmixing”, IEEE Signal Processing Magazine, vol. 31(1), pp. 67-81, January 2014.
  6. JMP. Nascimento and JMB. Dias, ”Vertex component analysis: a fast algorithm to unmix hyperspectral data”, IEEE TGRS, vol. 43(4), pp. 898-910, April 2005.
  7. J. Marot and S. Bourennane, ”Leaf marker spectra identification by hyperspectral image acquisition and vertex component analysis”, EUVIP'13, pp. 190-195, June 2013.
  8. Q. Du, I. Kopriva, and H. Szu, ”Investigation on Constrained Matrix Factorization for Hyperspectral Image Analysis”, In procs. of IEEE International Geoscience and Remote Sensing Symposium, vol. 6, pp. 4304-4306, Seoul, July 2005.
  9. N. Gillis and F. Glineur, ”Using underapproximations for sparse nonnegative matrix factorization”, Pattern Recognition, Vol. 43(4), April 2010, pp. 1676-1687.
  10. P. O. Hoyer, ”Non-negative matrix factorization with sparseness constraints”, Journal of Machine Learning Research, vol. 5, pp. 1457-1469, 2004.
  11. D. Muti, S. Bourennane, and J. Marot, ”Lower-Rank Tensor Approximation and Multiway Filtering,” SIAM Journal on Matrix Analysis and Applications (SIMAX), vol. 30(3), pp. 1172-1204, September 2008.
  12. AK. Mahlein et. al, ”Recent advances in sensing plant diseases for precision crop protection,” Eur J Plant Pathol, vol. 133, pp. 197-209, May 2012.
  13. John P. Kerekes et. al., ”SHARE 2012: subpixel detection and unmixing experiments”, In Procs. SPIE 8743, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery, May 18, 2013.
  14. AK. Mahlein et. al., ”Hyperspectral Imaging for SmallScale Analysis of Symptoms Caused by Different Sugar Beet Diseases”, Plant Methods, vol. 8, no 3, pp. 1-13, 2012.
  15. L. Chaerle et al., ”Multicolor fluorescence imaging for early detection of the hypersensitive reaction to tobacco mosaic virus,” Journal of Plant physiology, vol. 164, pp. 253-262, March 2007.
Download


Paper Citation


in Harvard Style

Zidi A., Marot J., Spinnler K. and Bourennane S. (2015). Unmixing of Hyperspectral Images with Pure Prior Spectral Pixels . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-089-5, pages 153-158. DOI: 10.5220/0005311101530158


in Bibtex Style

@conference{visapp15,
author={Abir Zidi and Julien Marot and Klaus Spinnler and Salah Bourennane},
title={Unmixing of Hyperspectral Images with Pure Prior Spectral Pixels},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={153-158},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005311101530158},
isbn={978-989-758-089-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)
TI - Unmixing of Hyperspectral Images with Pure Prior Spectral Pixels
SN - 978-989-758-089-5
AU - Zidi A.
AU - Marot J.
AU - Spinnler K.
AU - Bourennane S.
PY - 2015
SP - 153
EP - 158
DO - 10.5220/0005311101530158