Classification simulation of RazakSAT satellite

Abstract

This study presents simulation of land cover classification for RazakSAT satellite. The simulation makes use of the spectral capability of Landsat 5 TM satellite that has overlapping bands with RazakSAT. The classification is performed using Maximum Likelihood (ML), a supervised classification method that is based on the Bayes theorem. ML makes use of a discriminant function to assign pixel to the class with the highest likelihood. Class mean vector and covariance matrix are the key inputs to the function and are estimated from the training pixels of a particular class. The accuracy of the classification for the simulated RazakSAT data is accessed by means of a confusion matrix. The results show that RazakSAT tends to have lower overall and individual class accuracies than Landsat mainly due to the unavailability of mid-infrared bands that hinders separation between different plant types.