Study of Object-Oriented Based Remote Sensing Image Classification

A limitation in efficiently applying image classification is often represented by the spatial resolution of the image.By merging the multi resolution remote sensing image,importing the object(oriented) based idea,it effectively renewed the low resolution problem of multi-spectral images.This method was made up of a series of image segmentation and classification technique.First,the orthograph revised SPOT image was segmented by applying a region-based segmentation algorithm.Based this reference map,TM image was classified using the maximum likelihood classifier and additional empirical rules.Finally,the resulting land cover map was tested for accuracy and gained some effects.