Combination of radar and optical remote sensing data for land cover/use mapping

This paper addresses the advantage of combining spaceborne optical data with ALOS PALSAR polarimetric data for land cover/use mapping. We applied the most popular Maximum Likelihood classifier for land cover classification in the southern part of Kedah landscapes including area of settlements, forest, agriculture and water body. For classification purposes six classes (water, urban, forest, oil palm, bare land and paddy) were examined. For this study area, multisensor datasets were digitally integrated with training area based on the statistical values and ground references data derived from field visitation. Three general processing techniques included spatial filtering, texture measure and sensor combination were examined. These results show that radar results can be improved by various manipulations such as derived texture measures and filtering. Sensor combination greatly improved results, that achieved the highest overall accuracy. The systematic strategy of this study, determination of the best individual method before introducing the next procedure, was effective in managing a very complex, almost infinite set of analysis possibilities.