Nonlinear Estimation of Hyperspectral Mixture Pixel Proportion Based on Kernel Orthogonal Subspace Projection

  • Bo Wu
  • Liangpei Zhang
  • Pingxiang Li
  • Jinmu Zhang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3971)


A kernel orthogonal subspace projection (KOSP) algorithm has been developed for nonlinear approximating subpixel proportion in this paper. The algorithm applies linear regressive model to the feature space induced by a Mercer kernel, and can therefore be used to recursively construct the minimum mean squared-error regressor. The algorithm includes two steps: the first step is to select the feature vectors by defining a global criterion to characterize the image data structure in the feature space; and the second step is the projection onto the feature vectors and then apply the classical linear regressive algorithm. Experiments using synthetic data degraded by an AVIRIS image have been carried out, and the results demonstrate that the proposed method can provide excellent proportion estimation for hyperspectral images. Comparison with support vector regression (SVR) and radial basis function neutral network (RBF) had also been given, and the experiments show that the proposed algorithm slightly outperform than RBF and SVR.


Root Mean Square Error Feature Vector Radial Basis Function Support Vector Regression Hyperspectral Image 
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. 1.
    Cross, A.M., Settle, J.J., Drake, N.A., Paivinen, R.T.: Subpixel Measurement of Tropical Forest Cover Using AVHRR Data. Int. J. Remote Sensing 12(5), 1119–1129 (1991)CrossRefGoogle Scholar
  2. 2.
    Hu, Y.H., Lee, H.B., Scarpace, F.L.: Optimal Linear Spectral Unmixing. IEEE Trans. Geosci. Remote Sensing 37(1), 639–644 (1999)CrossRefGoogle Scholar
  3. 3.
    Mustard, J.F., Li, L., He, G.: Nonlinear Spectral Mixture Modeling of Lunar Multispectral Data: Implications for Lateral Transport. J. Geophys. Res. 103(E8), 19419–19425 (1998)CrossRefGoogle Scholar
  4. 4.
    Ren, H., Chang, C.-I.: A Generalized Orthogonal Subspace Projection Approach to Unsupervised Multispectral Image Classification. IEEE Trans. Geosci. Remote Sensing 39(8), 2515–2528 (2000)Google Scholar
  5. 5.
    Anouar, F., Badran, F., Thiria, S.: Probabilistic Self Organizing Map and Radial Basis Function. Neurocomput. 20(8), 83–96 (1998)MATHCrossRefGoogle Scholar
  6. 6.
    Guilfoyle, K.J., Althouse, M.L., Chang, C.-I.: A Quantitative and Comparative Analysis of Linear And Nonlinear Spectral Mixture Models Using Radial Basis Function Neural Networks. IEEE Trans. Geosci. Remote Sensing 39(8), 2314–2318 (2001)CrossRefGoogle Scholar
  7. 7.
    Vapnik, V.N.: The Nature of Statistical Learning Theory, 2nd edn. Springer, Heidelberg (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Bo Wu
    • 1
    • 2
  • Liangpei Zhang
    • 1
  • Pingxiang Li
    • 1
  • Jinmu Zhang
    • 3
  1. 1.State Key Lab of Information Engineering in Surveying, Mapping & Remote SensingWuhan UniversityWuhanChina
  2. 2.Spatial Information Research CenterFuzhou UniversityFuzhouChina
  3. 3.School of Civil EngineeringEast China Institute of TechnologyFuzhouChina

Personalised recommendations