Texture analysis of high resolution satellite imagery for mapping invasive plants

Abstract

In order to determine the status of an invasive plant species (Leucaena leucocephala) in southern Taiwan, a high resolution remote sensing image analysis system was developed based on the texture analysis. The developed system uses gray level co-occurrence matrix (GLCM) to extract spatial features from images to help distinguish target species from other vegetation types in the study site. Texture features are collected using three statistical measures from GLCM matrices and then used to fortify a supervised classification for mapping the target and other vegetation types. Test results demonstrated here indicate that the developed texture supplemented analysis can produce accurate mapping result of the target invasive plant species in the study site.