Automated unmixing consists of finding the number of endmembers, their spectral signatures and their abundances from a hyperspectral image. Most unmixing techniques are pixel-to-pixel procedures that do not take advantage of spatial information provided by hyperspectral sensor. This paper explores a new approach for unmixing analysis of hyperspectral imagery based on a multiscale representation for the joint estimation of the number of endmember and their spectral signatures. Experimental results using an AVIRIS image is presented.

Date Published: 24 May 2012
PDF: 11 pages
Proc. SPIE 8390, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVIII, 83901O (24 May 2012); doi: 10.1117/12.920698

Published in SPIE Proceedings Vol. 8390:
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVIII
Sylvia S. Shen; Paul E. Lewis, Editor(s)