Closed-form detector for solid sub-pixel targets in multivariate t-distributed background clutter

TL;DR

This paper introduces a closed-form GLRT-based detector for solid sub-pixel targets in hyperspectral images with multivariate t-distributed backgrounds, extending previous Gaussian-based methods and demonstrating effective performance in simulations.

Contribution

It provides the first closed-form detector for sub-pixel targets in fat-tailed t-distributed backgrounds, generalizing prior Gaussian and elliptically-contoured background models.

Findings

Effective detection in simulated hyperspectral data

Generalizes previous Gaussian background detectors

Performs well across various parameter regimes

Abstract

The generalized likelihood ratio test (GLRT) is used to derive a detector for solid sub-pixel targets in hyperspectral imagery. A closed-form solution is obtained that optimizes the replacement target model when the background is a fat-tailed elliptically-contoured multivariate t-distribution. This generalizes GLRT-based detectors that have previously been derived for the replacement target model with Gaussian background, and for the additive target model with an elliptically-contoured background. Experiments with simulated hyperspectral data illustrate the performance of this detector in various parameter regimes.