Uncertainty Analysis for Remote Sensing Classification in the Context of Disaster Studies in Shanghai

摘要

Our study applies the object-oriented technology to extract urban green automatically,which could increase accuracy through evaluating and analyzing the quality of disaster spatial data by measuring the disfigurement points and disfigurement rate in disaster G1S based on error analysis.The study shows that for high resolution remote sensing images that the accuracy may increase about 20% based on objectoriented technology using remote sensing image processing software eCognition than based on traditional supervised classification method using software ERDAS.