CLASSIFICATION OF POLARIMETRIC-SAR DATA WITH NEURAL NETWORK USING COMBINED FEATURES EXTRACTED FROM SCATTERING MODELS AND TEXTURE ANALYSIS

Katmoko Ari Sambodo
Aniati Murni
Mahdi Kartasasmita

The International Journal of Remote Sensing and Earth Sciences (IJReSES)
Vol. 4 (2007)

This paper shows a study on an alternative method for classification of polarimetric-SAR data. The method is designed by integrating the comined features extracted from two scattering models(i.e., freeman decomposition model and cloud decomposition model) and textural analysis with distribution-free neural network classifier. The neural network classifier (wich is based on a feedforward back-propagation neural network architecture) properly exploits the information in the combined features for providing high accuracy classification result. The effectiveness of the proposed method is demonstrated using E-SAR polarimetric data acquired on the area of Penajam, East Kalimantan, Indonesia.