Dependent Component Analysis as a Tool for Blind Spectral Unmixing of Remote Sensed Images

CESAR F. CAIAFA; EMANUELE SALERNO; ARACELI N. PROTO; LORENZA FIUMI

Florence, Italy

Conferencia; European Signal Processing Conference - EUSIPCO 2006; 2006

EURASIP

In this work, we present a blind technique for the estima- tion of the material abundances per pixel (endmembers) in hyperspectral remote-sensed images. Classical spectral un- mixing techniques require the knowledge of the existing ma- terials and their spectra. This is a problem when no prior information is available. Some techniques based on indepen- dent component analysis did not prove to be very efcient for the strong dependence among the material abundances always found in real data. We approach the problem of blind endmember separation by applying the MaxNG algorithm, which is capable to separate even strongly dependent signals. We also present a minimum-mean-squared-error method to estimate the unknown scale factors by exploiting the source constraint. The results shown here have been obtained from either synthetic or real data. The synthetic images have been generated by a noisy linear mixture model with real, spa- tially variable, endmember spectra. The real images have been captured by the MIVIS airborne imaging spectrometer. Our results showed that MaxNG is able to separate the end- members successfully if a linear mixing model holds true and for low noise and reduced spectral variability conditions.