Share Email Print

Proceedings Paper

A generalized linear mixing model for hyperspectral imagery
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We continue previous work that generalizes the traditional linear mixing model from a combination of endmember vectors to a combination of multi-dimensional affine endmember subspaces. This generalization allows the model to handle the natural variation that is present is real-world hyperspectral imagery. Once the endmember subspaces have been defined, the scene may be demixed as usual, allowing for existing post-processing algorithms (classification, etc.) to proceed as-is. In addition, the endmember subspace model naturally incorporates the use of physics-based modeling approaches ('target spaces') in order to identify sub-pixel targets. In this paper, we present a modification to our previous model that uses affine subspaces (as opposed to true linear subspaces) and a new demixing algorithm. We also include experimental results on both synthetic and real-world data, and include a discussion on how well the model fits the real-world data sets.

Paper Details

Date Published: 11 April 2008
PDF: 11 pages
Proc. SPIE 6966, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIV, 69661B (11 April 2008); doi: 10.1117/12.782113
Show Author Affiliations
David Gillis, Naval Research Lab. (United States)
Jeffrey Bowles, Naval Research Lab. (United States)
Emmett J. Ientilucci, Rochester Institute of Technology (United States)
David W. Messinger, Rochester Institute of Technology (United States)

Published in SPIE Proceedings Vol. 6966:
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIV
Sylvia S. Shen; Paul E. Lewis, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?