DMCA
Nonlinear Unmixing of Hyperspectral Data Based on a Linear-Mixture/Nonlinear-Fluctuation Model
| Citations: | 15 - 6 self |
BibTeX
@MISC{Chen_nonlinearunmixing,
author = {Jie Chen and Student Member and Cédric Richard and Senior Member and Paul Honeine},
title = {Nonlinear Unmixing of Hyperspectral Data Based on a Linear-Mixture/Nonlinear-Fluctuation Model},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract—Spectral unmixing is an important issue to analyze remotely sensed hyperspectral data. Although the linear mixture model has obvious practical advantages, there are many situations in which it may not be appropriate and could be advantageously replaced by a nonlinear one. In this paper, we formulate a new kernel-based paradigm that relies on the assumption that the mixing mechanism can be described by a linear mixture of endmember spectra, with additive nonlinear fluctuations defined in a reproducing kernel Hilbert space. This family of models has clear interpretation, and allows to take complex interactions of endmembers into account. Extensive experiment results, with both synthetic and real images, illustrate the generality and effectiveness of this scheme compared with state-of-the-art methods. Index Terms — Hyperspectral imaging, multi-kernel learning, nonlinear spectral unmixing, support vector regression.
Keyphrases
nonlinear unmixing linear-mixture nonlinear-fluctuation model hyperspectral data extensive experiment result real image abstract spectral unmixing sensed hyperspectral data clear interpretation additive nonlinear fluctuation support vector regression nonlinear spectral unmixing obvious practical advantage many situation complex interaction mixing mechanism linear mixture model index term hyperspectral imaging state-of-the-art method new kernel-based paradigm endmember spectrum important issue multi-kernel learning reproducing kernel hilbert space linear mixture
