Hostname: page-component-cd9895bd7-q99xh Total loading time: 0 Render date: 2024-12-26T17:08:47.306Z Has data issue: false hasContentIssue false
  • English
  • Français

Supervised Nonlinear Unmixing of Hyperspectral Images Using a Pre-image Methods

Published online by Cambridge University Press:  13 March 2013

N. H. Nguyen ,
J. Chen ,
C. Richard ,
P. Honeine  and
C. Theys
N. H. Nguyen
Affiliation:
Université de Nice Sophia-Antipolis, CNRS, Observatoire de la Côte d’Azur, France
J. Chen
Affiliation:
Université de Nice Sophia-Antipolis, CNRS, Observatoire de la Côte d’Azur, France Université de Technologie de Troyes, CNRS, France
C. Richard
Affiliation:
Université de Nice Sophia-Antipolis, CNRS, Observatoire de la Côte d’Azur, France
P. Honeine
Affiliation:
Université de Technologie de Troyes, CNRS, France
C. Theys
Affiliation:
Université de Nice Sophia-Antipolis, CNRS, Observatoire de la Côte d’Azur, France
Get access

Abstract

Spectral unmixing is an important issue to analyze remotely sensed hyperspectral data. This involves the decomposition of each mixed pixel into its pure endmember spectra, and the estimation of the abundance value for each endmember. Although linear mixture models are often considered because of their simplicity, there are many situations in which they can be advantageously replaced by nonlinear mixture models. In this chapter, we derive a supervised kernel-based unmixing method that relies on a pre-image problem-solving technique. The kernel selection problem is also briefly considered. We show that partially-linear kernels can serve as an appropriate solution, and the nonlinear part of the kernel can be advantageously designed with manifold-learning-based techniques. Finally, we incorporate spatial information into our method in order to improve unmixing performance.

Type
Research Article
Information
European Astronomical Society Publications Series , Volume 59: New Concepts in Imaging: Optical and Statistical Models , 2013 , pp. 417 - 437
Copyright
© EAS, EDP Sciences 2013

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Altmann, Y., Dobigeon, N., McLaughlin, S., & Tourneret, J.-Y., 2011a, in Proc. IEEE IGARSS
Altmann, Y., Halimi, A., Dobigeon, N., & Tourneret, J.-Y., 2011b, in Proc. IEEE IGARSS
Arias, P., Randall, G., & Sapiro, G., 2007, in Proc. IEEE CVPR
Aronszajn, N., 1950, Trans. Amer. Math. Soc., 68, 337 CrossRef
Baldridge, A.M., Hook, S.J., Grove, C.I., & Rivera, G., 2009, Remote Sensing Env., 113, 711 CrossRef
Bengio, Y., Paiement, J.-F., Vincent, P., et al., 2003, in Proc. NIPS
Boardman, J., 1993, in Proc. AVIRIS, 1, 11
Broadwater, J., Chellappa, R., Banerjee, A., & Burlina, P., 2007, in Proc. IEEE IGARSS, 4041
Chen, J., Richard, C., Bermudez, J.-C.M., & Honeine, P., 2011, IEEE Trans. Sig. Proc., 59, 5225 CrossRef
Chen, J., Richard, C., & Honeine, P., 2013a, IEEE Trans. Geosci. Remote Sens.
Chen, J., Richard, C., & Honeine, P., 2013b, IEEE Trans. Sig. Proc., 61, 480 CrossRef
Cucker, F., & Smale, S., 2002, Bull. Am. Math. Soc., 39, 1 CrossRef
Dobigeon, N., Moussaoui, S., Coulon, M., Tourneret, J.-Y., & Hero, A.O., 2009, IEEE Trans. Sig. Proc., 57, 4355 CrossRef
Eckstein, J., & Bertsekas, D., 1992, Math. Prog., 55, 293 CrossRef
Fauvel, M., Tarabalka, Y., Benediktsson, J.A., Chanussot, J., & Tilton, J., 2012, Proc. IEEE, to appear
Goldstein, T., & Osher, S., 2009, SIAM J. Imaging Sci., 2, 323 CrossRef
Halimi, A., Altmann, Y., Dobigeon, N., & Tourneret, J.-Y., 2011, IEEE Trans. Geosci. Remote Sens., 49, 4153 CrossRef
Ham, J., Lee, D. D., Mika, S., & Schölkopf, B., 2003, A kernel view of the dimensionality reduction of manifolds, Tech. Rep. TR-110 (Max-Planck-Institut für biologische Kybernetik)
Hapke, B., 1981, J. Geophys. Res., 86, 3039 CrossRef
Heinz, D.C., & Chang, C.-I., 2001, IEEE Trans. Geosci. Remote Sens., 39, 529 CrossRef
Honeine, P., & Richard, C., 2011, IEEE Signal Proc. Mag., 28, 77 CrossRef
Honeine, P., & Richard, C., 2012, IEEE Trans. Geosci. Remote Sens., 50, 2185 CrossRef
Iordache, M.-D., Bioucas-Dias, J.-M., & Plaza, A., 2011, in Proc. IEEE WHISPERS
Jutten, C., & Karhunen, J., 2003, in Proc. ICA, 245
Keshava, N., & Mustard, J.F., 2002, IEEE Signal Proc. Mag., 19, 44 CrossRef
Kwok, J., & Tsang, I., 2003, in Proc. ICML
Li, J., Bioucas-Dias, J.-M., & Plaza, A., 2011, IEEE Trans. Geosci. Remote Sens., 50, 809 CrossRef
Martin, G., & Plaza, A., 2011, IEEE Geosci. Remote Sens. Lett., 8, 745 CrossRef
Mika, S., Schölkopf, B., Smola, A., et al., 1999, in Proc. NIPS
Muñoz, A., & Diego, I.M., 2006, in Lecture Notes in Computer Science, Structural, Syntactic, and Statistical Pattern Recognition, Vol. 4109, ed. D.-Y. Yeung, J. Kwok, A. Fred, F. Roli & D. Ridder (Springer), 764
Nascimento, J.M.P., & Bioucas-Dias, J.M., 2005, IEEE Trans. Geosci. Remote Sens., 43, 898 CrossRef
Nascimento, J.M.P., & Bioucas-Dias, J.-M., 2009, in Proc. SPIE, 7477
Nguyen, N.H., Richard, C., Honeine, P., & Theys, C., 2012, in Proc. IEEE IGARSS
Raksuntorn, N., & Du, Q., 2010, IEEE Geosci. Remote Sens. Lett., 7, 836 CrossRef
Rogge, D.M., Rivard, B., Zhang, J., et al., 2007, Remote Sensing Env., 110, 287 CrossRef
Roweis, S., & Saul, L., 2000, Science, 2323
Schölkopf, B., Herbrich, R., & Williamson, R., 2000, A generalized representer theorem, Tech. Rep. NC2-TR-2000-81, NeuroCOLT, Royal Holloway College (University of London, UK)
Tenenbaum, J.B., de Silva, V., & Langford, J.C., 2000, Science, 290, 2319 CrossRef
Themelis, K., Rontogiannis, A.A., & Khoutroumbas, K., 2010, in Proc. IEEE ICASSP, 1194
Theys, C., Dobigeon, N., Tourneret, J.-Y., & Lanteri, H., 2009, in Proc. IEEE SSP
Tourneret, J.-Y., Dobigeon, N., & Chang, C.-I., 2008, IEEE Trans. Sig. Proc., 5, 2684
Winter, M.E., 1999, Proc. SPIE Spectrometry V, 3753, 266 CrossRef
Zortea, M., & Plaza, A., 2009, IEEE Trans. Geosci. Remote Sens., 47, 2679 CrossRef