Statistical Characterization of Natural Hyperspectral Backgrounds

The objective of this paper is the statistical characterization of natural hyperspectral backgrounds using multivariate probability distribution models. We consider models based on elliptically contoured t-distributions and threshold models based on extreme value theory. Both models provide a level of accuracy for the "heavy-tails" of hyperspectral backgrounds, which is necessary for the implementation of constant false alarm rate detectors and their performance evaluation. The performance of these models is illustrated using data from the AVIRIS sensor.