Go to Paper
Return to GeoComputation 99 Index

On Information Extraction Principles for Hyperspectral Data

LANDGREBE, David (landgreb@ecn.purdue.edu), Purdue University, School of Electrical & Computer Engineering, West Lafayette IN 47907-1285

Key Words: hyperspectral data, signal spaces, hyperspectral analysis

Means for optimally analyzing hyperspectral data have been a topic of study for some years. Our work has specifically focused on this topic since 1986. The point of departure for our study has been signal theory and the signal processing principles that have primarily grown from the communication sciences area over the last half century. The basic approach has been to seek a more fundamental understanding of high dimensional signal spaces in the context of multispectral remote sensing, and then to use this knowledge to extend the methods of conventional multispectral analysis to the hyperspectral domain in an optimal or near optimal fashion. The purpose of this paper is to outline what has been learned thus far.

The introduction of hyperspectral sensors that produce much more detailed spectral data than those previously, provides enhanced abilities to extract useful information from the data stream they produce. In theory, it is possible to discriminate successfully between any specified set of classes of data by increasing the dimensionality of the data far enough. In fact, current hyperspectral data, which may have from a few to several hundreds of bands, essentially makes this possible; however, it also is the case that this more detailed data requires more sophisticated data analysis procedures if their full potential is to be achieved. Much of what has been learned about the necessary procedures is not particularly intuitive, and indeed, in many cases is counter-intuitive. In this paper, we attempt not only to illuminate some of these counter-intuitive aspects, but to illustrate the practical methods that will make optimal analysis procedures possible.