TY - GEN
T1 - Endmember constrained semi-supervised hyperspectral unmixing
AU - Sigurdsson, Jakob
AU - Ulfarsson, Magnus O.
AU - Sveinsson, Johannes R.
N1 - Funding Information: This work was supported by the Icelandic Research Fund (130635-051) and the University of Iceland Research Fund. Publisher Copyright: © 2014 IEEE.
PY - 2014/6/28
Y1 - 2014/6/28
N2 - In this paper an endmember constrained semi-supervised hyperspectral unmixing method is proposed. The linear model is used to represent the hyperspectral data. A priori information about the endmembers is incorporated into the objective function with soft regularization. This information can be acquired from a spectral library or from the data itself. Quantitative evaluation of the method is done using simulated data and it is shown the soft regularization can yield better results than hard regularization. The method is also applied on a real hyperspectral data set and the estimated abundance maps improve when a priori information is used to aid the unmixing.
AB - In this paper an endmember constrained semi-supervised hyperspectral unmixing method is proposed. The linear model is used to represent the hyperspectral data. A priori information about the endmembers is incorporated into the objective function with soft regularization. This information can be acquired from a spectral library or from the data itself. Quantitative evaluation of the method is done using simulated data and it is shown the soft regularization can yield better results than hard regularization. The method is also applied on a real hyperspectral data set and the estimated abundance maps improve when a priori information is used to aid the unmixing.
KW - Hyperspectral unmixing
KW - regression
KW - semi-supervised unmixing
UR - https://www.scopus.com/pages/publications/85038557784
U2 - 10.1109/WHISPERS.2014.8077638
DO - 10.1109/WHISPERS.2014.8077638
M3 - Conference contribution
T3 - Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing
BT - 2014 6th Workshop on Hyperspectral Image and Signal Processing
PB - IEEE Computer Society
T2 - 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2014
Y2 - 24 June 2014 through 27 June 2014
ER -