Automated Gaussian spectral clustering of hyperspectral data

Unsupervised classification of multispectral and hyperspectral data is useful for a range of military and commercial remote sensing applications. These include terrain categorization, material detection and identification, and land use quantification. Here we show the development and application of an adaptive Gaussian Spectral Clustering approach to unsupervised classification and anomalous target detection in hyperspectral data. The method is built on adaptively estimating the parameters of a Gaussian mixture model from over local regions, and includes methods for adjusting to inevitable non-stationarity of hyperspectral image data. The algorithm is suitable for application to streaming hyperspectral data as would be required for real-time applications. In this paper we outline the model used, estimation techniques, and methods for adaptively estimating key model parameters required to characterize hyperspectral imagery. The key elements of the approach are demonstrated on reflective band hyperspectral data from NRL WarHORSE and NASA AVIRIS hyperspectral imagery. We also demonstrate broader utility with an example of segmentation of RADARSAT SAR imagery of sea ice.