Polarimetric contrast classification of agricultural fields using MAESTRO 1 AIRSAR data

Publisher Website
Google Scholar
Abstract
In this paper, we show the results of a polarimetric contrast classifier applied to the MAESTRO I JPL-AIRSAR data of agricultural fields. For the Dutch Flevoland agricultural site, we first compare the classifier's performance to results given in earlier studies, where polarimetric information was not available. This comparison shows that the availability of the measurements of the full polarimetric covariance matrix greatly enhances single-date classification accuracy. In the next step, we illustrate the use of frequency diverse classification results for further separation within specific classes. Furthermore, we will show the use of the classifierin two unsupervised approaches. In the first approach, we define the training clases from theoretical and semi-empirical models and run the classifier on a fully calibrated Fievoland dataset. In the second approach, we take covariance matrices extracted from the Flevoland data as the training set and use these in an unsupervised classification of the U.K. Feltwell agricultural site.

This publication has 15 references indexed in Scilit: