A linear transformation was recently recommended for application on hyperspectral imagery. This note shows that the method is completely equivalent to extracting proportional ground cover by standard means, but is less efficient than the more usual methods of spectral unmixing.
No takes yet. Share an insight, caveat, or question.
J.J. Settle (1996) studied this question.
Synapse has enriched one closely related paper. Consider it for comparative context: