Clustering hyperspectral imagery for improved adaptive matched filter performance

This paper offers improvements to adaptive matched filter (AMF) performance by addressing correlation and non-homogeneity problems inherent to hyperspectral imagery (HSI). The estimation of themeanvector and covariancematrix of the background should be calculated using “target-free” data. This statement reflects the difficulty that including target data in estimatesof themeanvectorandcovariancematrixof thebackgroundcouldentail.Thisdatacouldactas statistical outliers and severely contaminate the estimators. This fact serves as the impetus for a 2-stageprocess: First, attempt to remove the target data from thebackgroundbywayof the employment of anomaly detectors. Next, with remaining data being relatively “target-free” the way is cleared for signature matching. Relative to the first stage, we were able to test seven different anomaly detectors, some of which are designed specifically to deal with the spatial correlation ofHSI data and/or the presence of anomalous pixels in local or globalmean and covariance estimators. Relative to the second stage,we investigated the use of cluster analyticmethods to boost AMF performance.The researchshows that accounting forspatialcorrelationeffects in thedetectoryields nearly“target-free”data for use in anAMFthat is greatlybenefitted through theuseof cluster analysis methods. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI. [DOI: 10.1117/1.JRS.7.073547]