Analysis of agricultural imagery acquired by the TRWIS III hyperspectral sensor

The TRW Imaging Spectrometer III (TRWIS III) airborne hyperspectral sensor collects imagery in 384 contiguous spectral channels covering the 400 nm to 2450 nm wavelength range. For more than five years, the TRWIS III sensor has been used to acquire data for a variety of remote sensing applications. In a current, ongoing project, TRWIS III has gathered more than 50 Gigabytes of agricultural image data. This paper described images that were obtained in this experiment and the subspace projection technique that was used to analyze the imagery. This approach first reduces the data dimensionality by projecting test data onto the space spanned by the training data. Then a minimum distance measure from the means of the training data class clusters is used as the pixel classification criterion. An example is shown in which image pixels are classified using different spectral band combinations.