Abstract
Microwave Remote Sensing data have been widely used for land cover classification in our environment. In this study, ALOS PALSAR polarization bands were used to identify land cover features in three study areas in Malaysia. The study area consists of Penang, Perak and Kedah. The aims of this research are to investigate the performance of ALOS PALSAR datasets which are assessed independently and combination of these data with ALOS AVNIR-2 for land cover classification. Standard supervised classification method Maximum Likelihood Classifier (MLC) was applied. Various land cover classes were identified and assessed using the Transformed Divergence (TD) separability measures. The PALSAR data training areas were chosen based on the information obtained from ALOS AVNIR-2 datasets. The original data gave very poor results in identifying land cover classes due to the presence of immense speckle. The extraction and use of mean texture measures was found to be very advantageous when evaluating the separability among the different land covers. Hence, mean texture was capable to provide higher classification accuracies as compared to the original radar. The highest overall accuracy was achieved by combining the radar mean texture with ALOS AVNIR-2 data. This study proved that the land cover of Penang, Perak, and Kedah can be mapped accurately using combination of optical and radar data.
Export citation and abstract BibTeX RIS
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.