Kapitel/Beitrag aus dem Buch: Längle, T et al. 2013. OCM 2013 – Optical Characterization of Materials – conference proceedings.
Hyperspectral sensors are used to identify materials via
spectroscopic analysis. Often, the measured spectra consist of
mixed materials and depending on the problem, the mixture ratio
and the pure material spectra are wanted. In this paper, linear
spectral unmixing is performed using the Nonnegative Matrix
Factorization to analyze its correlation to ground truth data. The
results are compared to Nonnegative Least Squares unmixing using
manually selected endmembers from the image. Additionally,
the effect of different endmember extraction algorithms and
abundance initialization methods for NMF are investigated. To
test the validity of the method, several checkerboard patterns of
different ground minerals/rocks with predefined mixtures were
prepared. It was shown that good initialization is beneficial in
terms of approximation error and correlation to ground truth.
Gross, W et al. 2013. Evaluation of spectral unmixing usingnonnegative matrix factorization on stationaryhyperspectral sensor data of specificallyprepared rock and mineral mixtures. In: Längle, T et al (eds.), OCM 2013 – Optical Characterization of Materials – conference proceedings. Karlsruhe: KIT Scientific Publishing. DOI: https://doi.org/10.58895/ksp/1000032143-16
No license information is available about this publication.
Dieses Buch ist Peer reviewed. Informationen dazu Hier finden Sie mehr Informationen zur wissenschaftlichen Qualitätssicherung der MAP-Publikationen.
Veröffentlicht am 6. März 2013