AGRICULTURE CLASSIFICATION USING POLSAR DATA

摘要

In this paper a classification scheme is presented, that uses a knowledge-based approach, where the crops are first classifiedrninto broad classes, I.e. bare surfaces, cereal crops, root crops, spring crops, winter crops etc. Hereafter, the discriminationrnbetween the individual crop types within these broad categories is performed. The discrimination into thernbroad classes is performed using standard polarimetric parameters such as the backscatter coefficients both at linear andrncircular polarisations, correlation coefficient and phase difference. The classification into the individual crop types isrnpossible for some of the crop types, whereas it may for instance be very difficult to discriminate between some of therncereal crops. This part of the classification process is not as well established as the first part, and both a supervisedrnapproach and a knowledge-based approach may be used. Both POLSAR and PolInSAR data may be included in thernclassification scheme.rnThe classification approach has been evaluated using data from the Danish EMISAR, and quantitative results based onrnin-situ information are presented.