Mapping intimate mixtures using an adaptive kernel-based technique

In previous work, kernel methods were introduced as a way to generalize the linear mixing model for hyperspectral data. This work led to a new adaptive kernel unmixing method that both identified and unmixed linearly and intimately mixed pixels. However, the results from this previous research was limited to lab-based data where the endmembers were known a-priori and atmospheric effects were absent. This paper documents the results of the adaptive kernel-based unmixing techniques on real-world hyperspectral data collected over Smith Island, Virginia, USA. The results show that the adaptive kernel unmixing method can readily identify where nonlinear mixtures exist in the image even when perfect knowledge of the endmembers and the reflectance cannot be known.

[1]  Chein-I Chang,et al.  Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery , 2001, IEEE Trans. Geosci. Remote. Sens..

[2]  D. Anderson,et al.  Algorithms for minimization without derivatives , 1974 .

[3]  Tian Han,et al.  Investigation of Nonlinearity in Hyperspectral Imagery Using Surrogate Data Methods , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Antonio Plaza,et al.  NONLINEAR NEURAL NETWORK MIXTURE MODELS FOR FRACTIONAL ABUNDANCE ESTIMATION IN AVIRIS HYPERSPECTRAL IMAGES , 2005 .

[5]  Mario Winter,et al.  N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral data , 1999, Optics & Photonics.

[6]  Karen H. Haskell,et al.  An algorithm for linear least squares problems with equality and nonnegativity constraints , 1981, Math. Program..

[7]  Amit Banerjee,et al.  A generalized kernel for areal and intimate mixtures , 2010, 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing.

[8]  Fred A. Kruse,et al.  1999 AIG/HyVista HyMap group shoot: commercial hyperspectral sensing is here , 2000, SPIE Defense + Commercial Sensing.

[9]  Charles M. Bachmann,et al.  Automatic classification of land cover on Smith Island, VA, using HyMAP imagery , 2002, IEEE Trans. Geosci. Remote. Sens..

[10]  Chein-I Chang,et al.  A quantitative and comparative analysis of linear and nonlinear spectral mixture models using radial basis function neural networks , 2001, IEEE Trans. Geosci. Remote. Sens..

[11]  Amit Banerjee,et al.  A comparison of kernel functions for intimate mixture models , 2009, 2009 First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing.

[12]  J. Blass,et al.  Symposium , 1979, The Lancet.

[13]  Rama Chellappa,et al.  Kernel fully constrained least squares abundance estimates , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[14]  Anthony Widjaja,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2003, IEEE Transactions on Neural Networks.

[15]  John F. Mustard,et al.  Photometric phase functions of common geologic minerals and applications to quantitative analysis of mineral mixture reflectance spectra , 1989 .