Applying polarimetric SAR interferometric data for forest classification

In this paper the potential of combining polarimetric and interferometric classification approaches to classify forest is evaluated. First, forest classes, obtained from the application of polarimetric classification algorithms based on second order statistical properties and scattering properties of the data, are examined for their correlations with ground truth measurements of forest types and growth stages. Then optimal coherences will be utilized to increase the separation between classes. Both supervised and unsupervised classifications will be compared, and a new forest classification technique will be developed. In addition, we will evaluate the effect of interferometric coherences on forest classification for various spatial and temporal baselines. KeywordsPolarimetric SAR; forest classification; polarimetric SAR interferometry