Hyperspectral Outlier Detector Based on ConditionalDistributions

摘要

An outlier detection algorithm for hyperspectral imaging based on likelihood ratio test is presented in this article.The null hypothesis tests if a test pixel is from the conditional distribution of the pixel given the backgroundsubspace and the alternative hypothesis tests if a test pixel is from the conditional distribution of the pixel giventhe target subspace. Using principal components for the complementary subspaces, a practical outlier detectoris developed and is compared to conventional outlier detectors using a VNIR hyperspectral imagery.