Robust Matched Filters for Hyperspectral Target Detection

The objective of this paper is to introduce a robust matched filter that takes the uncertainty or variability of target signatures into account. It is shown that, if we describe this uncertainty with an ellipsoid in the spectral space, we can design a matched filter that provides a response of the same magnitude for all spectra within this ellipsoid. Thus, by changing the size of this ellipsoid, we can control the "spectral selectivity" of the matched filter. Finally, we demonstrate the operation of the robust matched filter with real hyperspectral imaging data.