论文信息 - Estimation of overlapping spectral signatures from hyperspectral data - 字舞流文

Estimation of overlapping spectral signatures from hyperspectral data

A new method for spectral unmixing is developed. This method accounts for the nonnegativity of the mixing constants. Preliminary experiments to test the method are reported.

Joseph A. O'Sullivan | Daniel R. Fuhrmann | Donald L. Snyder | William H. Smith

[1] Peter Strobl,et al. Unmixing of simulated ASTER data with applications for the assessment of mining impacts in central Germany , 1998, Optics & Photonics.

[2] Bruce C. Kindel,et al. Atmospheric corrections: on deriving surface reflectance from hyperspectral imagers , 1997, Optics & Photonics.

[3] Joseph A. O'Sullivan,et al. Deblurring subject to nonnegativity constraints , 1992, IEEE Trans. Signal Process..

[4] C. Helstrom,et al. Compensation for readout noise in CCD images , 1995 .

[5] Joseph A. O'Sullivan,et al. Information-Theoretic Image Formation , 1998, IEEE Trans. Inf. Theory.

[6] S Kawata,et al. Estimation of component spectral curves from unknown mixture spectra. , 1984, Applied optics.

[7] Daniel R. Fuhrmann. Simplex shrink-wrap algorithm , 1999, Defense, Security, and Sensing.

[8] R. Michael Hord. Unmixing hyperspectral image pixels using Excel SOLVER , 1998, Optics & Photonics.

[9] K Sasaki,et al. Component analysis of spatial and spectral patterns in multispectral images. I. Basis. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[10] S Kawata,et al. Constrained nonlinear method for estimating component spectra from multicomponent mixtures. , 1983, Applied optics.

[11] I. Csiszár. Why least squares and maximum entropy? An axiomatic approach to inverse problems , 1990 .