Comparative Performance Of ALOS PALSAR Polarization Bands And Its Combination With ALOS AVNIR-2 Data For Land Cover Classification
Loading...
Date
2012
Authors
Sim, Chong Keat
Journal Title
Journal ISSN
Volume Title
Publisher
Universiti Sains Malaysia
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. ASF MapReady program from Alaska satellite Facility Geographical
Institute at the University of Alaska Fairbanks was used for the preprocessing of
ALOS PALSAR data. In addition, different image processing techniques included
Speckle Filtering, Texture measures, and Principal Component Analysis (PCA) were
applied to the ALOS PALSAR datasets. Standard supervised classification method
Maximum Likelihood Classifier (MLC) was applied to the ALOS PALSAR images
for land cover classification analysis. 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. Frost Filter significantly improved the
classification accuracies but still not adequate for accurate land cover classification.
Description
Keywords
Comparative performance of ALOS PALSAR polarization bands , combination with ALOS AVNIR-2 data for land cover classification