Title :
A graph-based method for non-linear unmixing of hyperspectral imagery
Author :
Rob Heylen;Dževdet Burazerović;Paul Scheunders
Author_Institution :
IBBT-Visionlab, University of Antwerp, Universiteitsplein 1, Building N, B-2610 Wilrijk, Belgium
Abstract :
In this paper, we present an unmixing algorithm that is capable to determine endmembers and their abundances in hyperspectral imagery under non-linear mixing assumptions. The algorithm is an based upon the popular N-findR method, but uses distances between points in spectral space instead of the spectral values. These distances are defined as shortest-path distances in a nearest-neighbor graph, hereby respecting the non-trivial geometry of the data manifold in the case of nonlinearly mixed pixels. This allows the algorithm to be applied under non-linear mixing conditions. A demonstration on artificial data is given.
Keywords :
"Pixel","Signal processing algorithms","Algorithm design and analysis","Hyperspectral imaging","Manifolds","Mathematical model","Equations"
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2010 IEEE International
Print_ISBN :
978-1-4244-9565-8
Electronic_ISBN :
2153-7003
DOI :
10.1109/IGARSS.2010.5649619