Supervised and Unsupervised Classification of PolSAR Images from SIR-C and ALOS/PALSAR Using PolSARPro

 SIR-C quad-pol MLC data acquired in 1994 and ALOS PALSAR quad-pol and dual pol SLC data acquired in 2006 and 2007 over several Indian sites have been processed using PolSARpro software for classification of various land features. The land features include ocean, clear water, settlements, agriculture fields, arid lands, grown and young forest, hilly terrain, mangrove forest, etc. Both unsupervised and supervised classifications techniques are used for classification. The classification technique used is based upon polarimetric decomposition classification parameters: Entropy, Anisotropy and Alpha. The test sites used are SIR-C Land C-band Kolkata city and its surroundings, ALOS PALSAR data over several areas covering West Bengal, Haryana, Rajasthan, Uttar Pradesh, and Mumbai. For Kolkata city we observed that classification results for Land C-bands are slightly different. Index Terms  Radar polarimetry, synthetic aperture radar, speckle, target decomposition, terrain classification.