Land Cover Classification of ALOS PALSAR Data Using Maximum Likelihood and Dual Mode Polarization

Microwave remote sensing data have been widely used in land cover and land use classification. the objective of this research paper is to investigate the feasibility of the multi-polarized alos-palsar data for land cover mapping. this paper presents the methodology and preliminary result including data acquisitions, data processing and data analysis. standard supervised classification techniques such as the maximum likelihood, minimum distance-to-mean, and parallelepiped were applied to the alos-palsar images in the land cover mapping analysis. the palsar data training areas were chosen based on the information obtained from optical satellite imagery. the best supervise classifier was selected based on the highest overall accuracy and kappa coefficient. this study indicated that the land cover of butterworth, malaysia can be mapped accurately using alos palsar data