Analysis of Hyperspectral Remote Sensing Images

  • Liangpei Zhang
  • Yanfei Zhong


Hyperspectral remote sensing, or known as imaging spectroscopy, is a recently developed technique since the last two decades of the 20th century (Chang 2003). Imaging spectroscopy is a relatively fully-fledged experimental tool that has been successfully used in the laboratory by physicists and chemists for over 100 years for identification of materials and their composition. Absorption features accord to the special chemical bound of a material, which can be calculated by imaging spectroscopy. With the demand of earth observation, imaging spectroscopy technique has extended to the detection and mapping of materials by satellite imagery. Since the 1980s, geologists have used sensors on the man-made satellite to obtain the spectrum of every position in a large scale in the ground which combines a datacube which combines the imaging and spectroscopy in a single system. That's to say that hyperspectral remote sensing not only contain spatial features but also spectral features of the ground objects. But it doesn't refer to the remote sensing imagery with only several bands, such as Landsat TM or Modis imagery. In fact, the most significant difference between hyperspectral remote sensing and these multispectral remote sensing is that it has much more bands with much higher spectral resolution. Hyperspectral remote sensing usually has over one hundred bands with a spectral resolution of under 10 nm. Fig. 9.1 shows the concept about hyperspectral remote sensing imagery which usually comprises of datacube with a series of images. In this case, it provides a better discrimination among similar targets. On the other hand, subtle spectral differences would be hidden in spectra acquired with multispectral remote sensing with broad spectral band sensors. Hyperspectral remote sensing has been widely used in many civil and military applications such as geology, agriculture, and global change, defense, intelligence, and law enforcement. The aim of the chapter is to discuss the basic data processing and analysis techniques for hyperspectral remote sensing such as feature selection, classification, mixed pixel unmixing etc.


Feature Selection Feature Subset Artificial Immune System Spectral Angle Mapper Antibody Population 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Adams JB, Smith MO, Johnson PE (1996) Spectral mixture modeling: A new analysis of rock and soil types at the Viking Lander 1 site. Journal of Geophysical Reserach 91: 2089–8112Google Scholar
  2. Bagan H., Wang Q, Watanabe M, Yang Y, Ma J (2005) Land cover classification from MODIS EVI times-series data using SOM neural network. International Journal of Remote Sensing 26: 4999–5012CrossRefGoogle Scholar
  3. Bandyopadhyay S, Maulik U, Mukhopadhyay A (2007) Multiobjective genetic clustering for pixel classification in remote sensing imagery. IEEE Transactions on Geoscience and Remote Sensing 45: 1506–1511CrossRefGoogle Scholar
  4. Bezdek JC (1981) Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum Press, New York.Google Scholar
  5. Borel CC, Gerstl SA (1986) Nonlinear spectral mixing models for vegetative and soil surface. Remote Sensing of Environment l: 8098–8112Google Scholar
  6. Bruzzone L, Roli F, Serpico SB (1995) An extension of the Jeffreys-Matusita distance to multiclass cases for feature selection. IEEE Trans. Geosci. Remote Sensing 33: 1318–1321CrossRefGoogle Scholar
  7. Burnet FM (1959) The Clonal Selection Theory of Acquired Immunity, Cambridge University Press Cambridge, U.K.Google Scholar
  8. Burnet FM (1978) Clonal selection and after. In: Bell G I, Perelson A S, Pimbley G H eds. Theoretical Immunology : 63–85 Marcel Dekker Inc, New YorkGoogle Scholar
  9. Campbell JB (2002) Introduction to Remote Sensing. Taylor & Francis, LondonGoogle Scholar
  10. Carter JH (2000) The immune system as a model for pattern recognition and classification. Journal of the American Medical Informatics Association 7: 28–41Google Scholar
  11. Chang CI (2003) Hyperspectral Imaging: Techniques for Spectral Detection and Classification. Orlando. FL: Kluwer, AcademicGoogle Scholar
  12. Chang CI, Wang S (2006) Constrained band selection for hyperspectral imgery. IEEE Trans. Geosci. Remote Sensing 44: 1575–1585CrossRefGoogle Scholar
  13. Cross AM, Settle JJ, Drake NA, Paivinen RT (1991) Subpixel measurement of tropical forest cover using AVHRR data. Int. J. Remote Sensing 12: 1119–1129CrossRefGoogle Scholar
  14. Dasgupta D (1999) Artificial Immune Systems and Their Applications. Springer, GermanyGoogle Scholar
  15. De Castro LN, Timmis J (2002) Artificial Immune systems: A New Computational Intelligence Approach. Springer-Verlag, London, U.K.Google Scholar
  16. De Castro LN, Von Zuben FJ (2002) Learning and optimization using the clonal selection principle. IEEE Transactions on Evolutionary Computation 6: 239–250CrossRefGoogle Scholar
  17. Dominique M, Alistair B (2003) Nonlinear blind source separation using kernels. IEEE Trans. On Neutral Networks 14: 228–234CrossRefGoogle Scholar
  18. Du Q, Chang CI (1999) An interference rejection-based radial basis function neural network for hyperspectral image classification. International Joint Conference on Neural Networks 4: 2698–2703Google Scholar
  19. Duda RO, Hart PE, Stork DG (2001) Pattern classification. 2nd edn. John Wiley & SonsGoogle Scholar
  20. Fukunaga K (1990) Introduction to Statistical Pattern Recognition. 2nd eds. New York: AcademicGoogle Scholar
  21. Gong P, Miller JR, Spanner M (1994) Forest canopy closure from classification and spectral unmixing of scene components - multisensor evaluation of an open canopy. IEEE Trans. Geosci. Remote Sensing 32: 1067–1080CrossRefGoogle Scholar
  22. Hall D, Ball G (1965) Isodata: a novel method of data analysis and pattern classification. Technical report, Stanford Research InstituteGoogle Scholar
  23. Hand, D J (1981) Discrimination and Classification. New York: Wiley.Google Scholar
  24. Hapke B (1981) Bidirectional reflectance spectroscopy 1. Theory. J. Geophys. Res 86: 3039–3054CrossRefGoogle Scholar
  25. Harmeling S, Ziehe A, Kawanabe M, Muller KR (2003) Kernel-based nonlinear blind source separation Neural Compute 15: 1089–1124Google Scholar
  26. Hu YH., Lee HB, Scarpace FL (1999) Optimal Linear Spectral Unmixing. IEEE Transactions on Geoscience and Remote Sensing 37: 639–644CrossRefGoogle Scholar
  27. Hughes GF (1968) On the mean accuracy of statistical pattern recognizers. IEEE Trans. Inf. Theory IT–14: 55–63CrossRefGoogle Scholar
  28. Jain A, Zongker D (1997) Feature selection: evaluation, application, and small sample performance. IEEE Trans. Pattern Anal. Machine Intell. 19: 153–158CrossRefGoogle Scholar
  29. Jensen JR (2005) Introductory digital image processing: A remote sensing perspective, 3rd edn. NJ Prentice Hall, Upper Saddle RiverGoogle Scholar
  30. Johnson PE, Smith MO, Adams JB (1992) Simple algorithms for remote determination of mineral abundances and particle sizes from reflectance spectra. Journal of Geophysical Research 97(E2): 2649–2657CrossRefGoogle Scholar
  31. Kaufman L, Rousseeuw P J (1990). Finding Groups in Data: An Introduction to Cluster Analysis. John Wiley & Sons, New YorkGoogle Scholar
  32. Kerri JG, Mark LA, Chang CI (2001) A Quantitative and Comparative Analysis of Linear and Nonlinear Spectral Mixture Models Using Radial Basis Function Neural Networks. IEEE Trans. Geosci. Remote Sensing 39: 2314–2318CrossRefGoogle Scholar
  33. Landgrebe DA (2002) Hyperspectral image data analysis. IEEE Signal Processing Magazine 19: 17–28CrossRefGoogle Scholar
  34. Lee C, Landgrebe DA (1993) Feature extraction based on decision boundaries. IEEE Transactions on Pattern Analysis and Machine Intelligence. 15: 388–400CrossRefGoogle Scholar
  35. Li J, Bruce LM, Mathur A (2002) Wavelet Transform for Dimensionality Reduction in Hyperspectral Linear Unmixing. IEEE Geoscience Remote Sensing Symposium 6: 3513–3515Google Scholar
  36. Liu W, Wu EY (2005) Comparison of non-linear mixture models: sub-pixel classification. Remote Sensing of Environment 94: 145–154CrossRefGoogle Scholar
  37. Mustard JF, Li L, He G (1998) Nonlinear spectral mixture modeling of lunar multispec- tral data: Implications for lateral transport. Journal of Geophysical Research 103: 19419–19425CrossRefGoogle Scholar
  38. Mustard JF, Pieters CM (1998) Photometric phase functions of common geologic minerals and applications to quantitative analysis of mineral mixture reflectance spectra. Journal of Geophysical Research 94: 13619–13634CrossRefGoogle Scholar
  39. Narendra PM, Fukunaga K (1977). A branch and bound algorithm for feature subset selection. IEEE Trans. Comput. C-31: 917–922CrossRefGoogle Scholar
  40. Pudil P, Novovicova J, Kittler J (1994) Floating search methods in feature selection. Pattern Recognit. Lett. 15: 1119–1125CrossRefGoogle Scholar
  41. Quarmby NA, Townshend JR, Settle JJ, White KH, Milnes M, Hindle TL, Silleos N (1992) Linear mixture modelling applied to AVHRR data for crop area estimation. Int. J. Remote Sensing 13: 415–425CrossRefGoogle Scholar
  42. Ren H, Chang CI (2000) A generalized orthogonal subspace projection approach to unsupervised multispectral image classification. IEEE Trans. Geosci. Remote Sensing 39: 2515–2528Google Scholar
  43. Richards JA (1986) An Introduction to Remote Sensing digital image analysis. Springer VerlagGoogle Scholar
  44. Schölkopf B, Smola AJ (2002) Learning with Kernels. MIT Press, Cambridge, MA.Google Scholar
  45. Sebastiano SB, Lorenzo L (2001) A new search algorithm for feature selection in hyperspectral remote sensing images. IEEE Trans. Geosci. Remote Sensing 39: 1360–1367CrossRefGoogle Scholar
  46. Settle J (2002) On constrained energy minimization and the partial unmixing of multispectral images. IEEE Trans. Geosci. Remote Sensing 40: 718–721CrossRefGoogle Scholar
  47. Settle J, Campbell N (1998) On the errors of two estimators of sub-pixel fractional cover when mixing Is linear. IEEE Trans. Geosci. Remote Sensing 36: 163–170CrossRefGoogle Scholar
  48. Smola AJ, Schölkopf B (2004) A tutorial on support vector regression. Statistics and Computing 14: 199–222CrossRefGoogle Scholar
  49. Smola AJ, Schölkopf B (2000) Sparse greedy matrix approximation for machine learning. International Conference on Machine Learning ICML Stanford, CA.Google Scholar
  50. Storvik G, Fjortoft R, Solberg AHS (2005) A Bayesian approach to classification of multiresolution remote sensing data. IEEE Trans.on Geosci. and Remote Sensing 43: 539–547CrossRefGoogle Scholar
  51. Swain PH, Davis SM (1978) Remote sensing: the quantitative approach. McGraw-Hill, New YorkGoogle Scholar
  52. Vapnik VN (1998) Statistical Learning Theory. Wiley, New YorkGoogle Scholar
  53. Vincent P, Bengio Y (2002) Kernel matching pursuit. Machine Learning Journal 48: 165–187CrossRefGoogle Scholar
  54. Webb A R (2002) Statistical Pattern Recognition. 2nd edn. John Wiley & Sons, Inc.Google Scholar
  55. Yamazaki T, Gingras D (1999) Unsupervised multispectral image classification using MRF models and VQ method. IEEE Transactions on Geoscience and Remote Sensing 37: 1173–1176CrossRefGoogle Scholar
  56. Yuhas RH, Goetz AFH, Boardman JW (1992) Discrimination Among Semi-Arid Landscape Endmembers Using the Spectral Angle Mapper (SAM) Algorithm. Summaries of the 4th JPL Airborne Earth Science Workshop: 147–149 JPL PublicationGoogle Scholar
  57. Zhang L, Li D (1998) Study of the spectral mixture model of soil and vegetation in PoYang lake area, China. Int. J. Remote Sensing 19: 2077–2084CrossRefGoogle Scholar
  58. Zhang L, Zhong Y, Huang B, Gong J, Li P (2007a) Dimensionality Reduction Based on Clonal Selection for Hyperspectral Imagery, IEEE Trans. In Geoscience and Remote Sensing 45: 4172–4185CrossRefGoogle Scholar
  59. Zhang L, Wu B, Huang B, Li P (2007b) Nonlinear Estimation of Subpixel Proportion Via Kernel Least Square Regression. Int.J.Remote Sensing 28: 4157–4172CrossRefGoogle Scholar
  60. Zhong Y, Zhang L., Huang B£¬Li P (2006) An Unsupervised Artificial Immune Classifier for Multi/hyper-spectral Remote Sensing Imagery. IEEE Trans. on Geosci. and Remote Sensing 44: 420–431CrossRefGoogle Scholar
  61. Zhong Y, Zhang L, Gong J, Li P (2007) A Supervised Artificial Immune Classifier for Remote Sensing Imagery. IEEE Trans. on Geosci. and Remote Sensing 45: 3957–3966CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • Liangpei Zhang
    • 1
  • Yanfei Zhong
    • 1
  1. 1.State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote SensingWuhan UniversityWuhanChina, People’s Republic

Personalised recommendations