An entropy based classification scheme for polarimetric SAR data

Considers a new unsupervised classification scheme for polarimetric SAR data. This scheme makes use of a local estimate of the scattering entropy in the scene to determine the number of discernible classes in the data. Examples are presented of application of the scheme to AIRSAR data provided by NASA/JPL.

[1]  Jin Au Kong,et al.  Classification of Earth Terrain Using Polarimetric Synthetic Aperture Radar Images , 1989, Progress In Electromagnetics Research.

[2]  Simon Yueh,et al.  Application of neural networks to radar image classification , 1994, IEEE Trans. Geosci. Remote. Sens..