Land Cover Feature Extraction and Analysis using Biogeography based Optimization (BBO) Algorithm
- Prabhjot Kaur, Kamaljit Kaur Dhillon, +5 authors quot
The classification of various land cover features using fully polarimetric Synthetic Aperture Radar (SAR) data sets is an important application of radar remote sensing. The data acquired is over various parts of India are SIR-C L- and C-band data over Kolkata city and its surroundings. The field work was carried out in April 2009. Similarly, PALSAR quad pol data over several areas is acquired. The proposed classifier is based on the artificial neural network which is developed in Matlab and it makes use of backscattering values. It is a supervised classification technique which is applied on the ALOS PALASR and SIR-C data. The classification accuracy after applying different speckle filters is compared with the classification accuracy obtained without applying filter. It is also compared with minimum distance and maximum likelihood techniques.