Context-based endmember detection for hyperspectral imagery

An endmember detection algorithm that simultaneously partitions an input data set into distinct contexts, estimates endmembers, number of endmembers, and abundances for each partition is presented. In contrast to previous endmember detection algorithms based on the convex geometry model, this method is capable of describing non-convex sets of hyperspectral pixels. Endmembers are found for non-convex regions by partitioning the set of pixels into convex regions using the Dirichlet process and determining unique endmembers for each region. This novel endmember detection method naturally produces a classifier with a reject class. The algorithm can effectively identify to which context a test data point belongs and identify test pixels for which the associated context is unknown. Results are shown on AVIRIS Indian Pines hyperspectral data. The results show the classification capability of this context-based endmember algorithm.