The fully adaptive GMRF anomaly detector for hyperspectral imagery

The use of hyperspectral imagery for remote sensing detection applications has received attention recently due to the ability of the hyperspectral sensor to provide registered information in both space and frequency. However, this coupling of spatial and spectral information leads to an immense amount of data for which it has proven difficult to develop an efficient implementation of the Maximum-Likelihood (ML) detector. In this paper we present the Gauss-Markov random field (GMRF) detector which we have developed for detecting man-made anomalies in hyperspectral imagery. The GMRF detector is the first computationally efficient ML-detector for hyperspectral imagery. We compare the detection performance and the computational requirements of our detector implementation to the benchmark RX detection algorithm for hyperspectral imagery.