Validation of Information Products of Airborne Hyperspectral Imagery Processing

Abstract

In regards to the problem of airborne hyperspectral imagery processing, most attention is paid to the construction of an automated classifier which implements computational procedures of recognizing forest vegetation of different species composition and age. The validation of the information products obtained as a result of processing the data of hyperspectral remote sensing is based on finding a maximum of a posteriori probability for selected classes of objects using the contemporary views of Markov random fields allowing a priori probabilities for each element of hyperspectral apparatus resolution to be calculated. The necessity of taking into account the noise component of the apparatus to enhance the accuracy of solving the applied problems under study is shown. Examples of comparing the data of hyperspectral imagery processing with the data of ground-based forest inventory for a selected territory are demonstrated.