Signal, Image and Video Processing

, Volume 9, Issue 4, pp 959–966 | Cite as

Sparse coding of hyperspectral imagery using online learning

Original Paper

Abstract

Sparse coding ensures to express the data in terms of a few nonzero dictionary elements. Since the data size is large for hyperspectral imagery, it is reasonable to use sparse coding for compression of hyperspectral images. In this paper, a hyperspectral image compression method is proposed using a discriminative online learning-based sparse coding algorithm. Compression and anomaly detection tests are performed on hyperspectral images from the AVIRIS dataset. Comparative rate–distortion analyses indicate that the proposed method is superior to the state-of-the-art hyperspectral compression techniques.

Keywords

Sparse coding Hyperspectral imagery Anomaly detection Online learning 

Notes

Acknowledgments

This work is supported in part by the Scientific and Technical Research Council of Turkey under National Young Researchers Career Development Program (3501 TUBITAK CAREER) grant with agreement number 114E200. Authors are grateful to Mustafa Teke for his assistance in obtaining RX detection results. An earlier version of this study was presented in part at the IEEE International Workshop on Computational Intelligence for Multimedia Understanding (IWCIM) 2014 [17].

References

  1. 1.
    Fauvel, M., Tarabalka, Y., Benediktsson, J.A., Chanussot, J., Tilton, J.C.: Advances in spectral-spatial classification of hyperspectral images. Proc. IEEE 101(3), 652–675 (2013)CrossRefGoogle Scholar
  2. 2.
    Frontera-Pons, J., Pascal, F., Ovarlez, J.P.: False-alarm regulation for target detection in hyperspectral imaging. In: 5th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, St. Martin, France, 15–18 Dec, pp. 161–164 (2013)Google Scholar
  3. 3.
    Eismann, M.T.: Hyperspectral Remote Sensing. SPIE, Bellingham (2012)CrossRefGoogle Scholar
  4. 4.
    Olshausen, B.A., Field, D.J.: Sparse coding with an overcomplete basis set: a strategy employed by V1? Vis. Res. 37(23), 3311–3325 (1997)CrossRefGoogle Scholar
  5. 5.
    Lee, H., Battle, A., Raina, R., Ng, A.Y.: Efficient sparse coding algorithms. In: Advances in Neural Information Processing Systems 19, NIPS, pp. 801–808 (2006)Google Scholar
  6. 6.
    Mairal, J., Bach, F., Ponce, J., Sapiro, G.: Online learning for matrix factorization and sparse coding. J. Mach. Learn. Res. 11, 19–60 (2010)MATHMathSciNetGoogle Scholar
  7. 7.
    Chen, S.S., Donoho, D.L., Saunders, M.A.: Atomic decomposition by basis pursuit. SIAM J. Sci. Comput. 20(1), 33–61 (1998)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Aharon, M., Elad, M., Bruckstein, A.: K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Signal Process. 54(11), 4311–4322 (2006)CrossRefGoogle Scholar
  9. 9.
    Chang, C.I.: Hyperspectral Data Processing: Algorithm Design and Analysis. Wiley, New York (2013)CrossRefGoogle Scholar
  10. 10.
    Magli, E., Gabriella, O., Emanuele, Q.: Optimized onboard lossless and near-lossless compression of hyperspectral data using CALIC. IEEE Geosc. Remote Sens. Lett. 1(1), 21–25 (2004)CrossRefGoogle Scholar
  11. 11.
    Bilgin, A., Zweig, G., Marcellin, M.W.: Three-dimensional image compression with integer wavelet transforms. Appl. Opt. 39(11), 1799–1814 (2000)CrossRefGoogle Scholar
  12. 12.
    Christophe, E.: Hyperspectral data compression tradeoff. In: Optical Remote Sensing. Springer, pp. 9–29 (2011)Google Scholar
  13. 13.
    Christophe, E., Corinne, M., Pierre, D.: Hyperspectral image compression: adapting SPIHT and EZW to anisotropic 3-D wavelet coding. IEEE Trans. Image Process. 17(12), 23346–23348 (2008)CrossRefGoogle Scholar
  14. 14.
    Bottou. L., Bousquet, O.: The tradeoffs of large scale learning. In: Advances in Neural Information Processing Systems 20, NIPS, pp. 161–168 (2007)Google Scholar
  15. 15.
    Charles, S., Olshausen, B.A., Rozell, C.J.: Learning sparse codes for hyperspectral imagery. IEEE J. Sel. Top. Signal Process. 5(5), 963–978 (2011)CrossRefGoogle Scholar
  16. 16.
    Wang, Z., Nasrabadi, N.M., Huang, T.S.: Spatial-spectral classification of hyperspectral images using discriminative dictionary designed by learning vector quantization. IEEE Trans. Geosci. Remote Sens. 52(8), 4808–4822 (2014)CrossRefGoogle Scholar
  17. 17.
    Ulku, I., Toreyin, B.U.: Lossy compression of hyperspectral images using online learning based sparse coding. In: Proceedings of International Workshop on Computational Intelligence for Multimedia Understanding (IWCIM), Paris, France, 1–2 Nov, pp. 1–5 (2014)Google Scholar
  18. 18.
    Koh, K., Kim, S., Boyd, S.: An interior-point method for large-scale l1-regularized logistic regression. J. Mach. Learn. Res. 8, 1519–1555 (2007)Google Scholar
  19. 19.
    Bertsekas, D.P.: Nonlinear Programming. Athena Scientific, Belmont, MA (1999)MATHGoogle Scholar
  20. 20.
    Reed, S.I., Yu, X.: Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distrihution. IEEE Trans. Acoust. Speech Signal Process. 38, 1760–1770 (1990)CrossRefGoogle Scholar
  21. 21.
    Kiely, A., Klimesh, M.: Exploiting calibration-induced artifacts in lossless compression of hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 47(8), 2672–2678 (2009)CrossRefGoogle Scholar
  22. 22.
    Mairal, J., Bach, F., Ponce, J., Sapiro, G.: Online dictionary learning for sparse coding. In: Proceedings of the 26th Annual International Conference on Machine Learning, ACM, Montreal, QC, Canada, 14–18 June, pp. 689–696 (2009)Google Scholar
  23. 23.
    Ricci, M., Magli, E.: Predictor analysis for onboard lossy predictive compression of multispectral and hyperspectral images. J. Appl. Remote Sens. 7(1), 074591–074591 (2013)CrossRefGoogle Scholar
  24. 24.
    Qian, D., Fowler, J.E.: Hyperspectral image compression using JPEG2000 and principal component analysis. IEEE Trans. Geosci. Remote Sens. 4(2), 201–205 (2007)CrossRefGoogle Scholar
  25. 25.
    Huo, C., Zhang, R., Yin, D., Wu, Q., Xu, D.: Hyperspectral data compression using sparse representation. In: 2012 4th Workshop on Hyperspectral Image and Signal Processing (WHISPERS), pp. 1–4 (2012)Google Scholar
  26. 26.
    Qian, D., Wei, Z., Fowler, J.E.: Anomaly-based hyperspectral image compression. In: 2008 IGARSS, IEEE International Geoscience and Remote Sensing Symposium, vol. 2, pp. 974–977 (2008)Google Scholar
  27. 27.
    Ngadiran, R., Boussakta, S., Bouridane, A., Syarif, B.: Hyperspectral image compression with modified 3D SPECK. In: 7th International Symposium on Communication Systems Networks and Digital Signal Processing (CSNDSP), pp. 806–810 (2010)Google Scholar
  28. 28.
    Gu, X., Wang, Y.: VLSI design of progressive lossy-to-lossless multispectral and hyperspectral image compression in spacecrafts and satellites. Inf. Eng. Lett. 3(1), 43–56 (2013)Google Scholar
  29. 29.
    Open Source MATLAB Hyperspectral Toolbox. 2012. Version 0.07. http://matlabhyperspec.sourceforge.net/. Accessed 24 Jan 2015
  30. 30.
    Di, W., Pan, Q., He, L., Cheng, Y.: Anomaly detection in hyperspectral imagery by fuzzy integral fusion of band-subsets. Photogramm. Eng. Remote Sens. 74(2), 201–213 (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2015

Authors and Affiliations

  1. 1.Department of Electrical and Electronics EngineeringÇankaya UniversityEtimesgutTurkey
  2. 2.Space Technologies Institute (UZAY), The Scientific and Technological Research Council of Turkey (TUBITAK)ODTÜ YerleşkesiAnkaraTurkey

Personalised recommendations