REMOTE SENSING TECHNIQUES FOR OIL PALM AGE CLASSIFICATION USING LANDSAT-5 TM SATELLITE

This paper demonstrates the procedure to classify the age of oil palm trees using Landsat-5 TM (thematic mapper) remote sensing data. The study was conducted in two phases: phase I focuses on the the land cover classification, and phase II involves the oil palm age classification. Firstly,the region of interest (ROI) was identified and drawn in order to supply the training and testing pixels for the supervised classification. Maximum likelihood (ML) classifier was used for land cover classification. The land cover classification using the ML produces a good result with an overall accuracy of 85.51% and kappa coefficient of 0.8208. Meanwhile, three classifiers were used to investigate the age of oil palm classification, which are the 1) Maximum likelihood (ML), 2) Neural Network (NN) and, 3) Support Vector Machine (SVM). The accuracy of the classifications was then assessed by comparing the classifications with a reference set using a confusion matrix technique. Among the three classifiers, SVM performs the best with the highest overall accuracy of 54.18% and kappa coefficient of 0.39.