Spatial/Spectral Modeling of Hyperspectral Data
Hyperspectral imaging (HSI) sensors are a relatively new type of camera that can capture several hundred channels of light over a wide range of wavelengths; by comparison, a standard color camera captures 3 channels (red, blue and green) over a relatively narrow wavelength range. The increased number of channels in hyperspectral data leads to a corresponding growth in the amount of information that can be extracted from an image. The tradeoff is an explosion in both the size (typical images can be on the order of 1 gigabyte) and complexity of the image data. We note that, by its very nature, HSI data contains both spatial and spectral (wavelength) information. In order to extract this information, a wide variety of different models have been introduced. Unfortunately, the vast majority of these models focus solely on the spectral side of the data. In this talk, we present a brief introduction to HSI data, including a review of the various (geometrical and statistical) models that are currently in use. We then introduce some preliminary thoughts on ways to extend these models to better incorporate both the spatial and spectral information present in the data. Audience participation is greatly encouraged.