Robust Matched Filters for Target Detection in Hyperspectral Imaging Data

Most detection algorithms for hyperspectral imaging applications assume a target with a perfectly known spectral signature. In practice, the target signature is either imperfectly measured (target mismatch) and/or it exhibits spectral variability. The objective of this paper is to introduce a robust matched filter that takes the uncertainty and/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. The ability of the robust matched filter to deal effectively with target mismatch and spectral variability is demonstrated with hyperspectral imaging data from the HYDICE sensor.