期刊名称：International Journal of Environment and Geoinformatics
电子版ISSN：2148-9173
出版年度：2015
卷号：2
期号：2
页码：63-76
DOI：10.30897/ijegeo.303545
语种：English
出版社：IJEGEO
摘要：This research aims to propose new rule sets to be used for object based classification of SPOT-5images to accurately create detailed urban land cover/use maps. In addition to SPOT-5 satelliteimages, Normalized Difference Vegetation Index (NDVI) and Normalized Difference Water Index(NDWI) maps, cadastral maps, Openstreet maps, road maps and Land Cover maps, were alsointegrated into classification to increase the accuracy of resulting maps. Gaziantep city, one of thehighly populated cities of Turkey with different landscape patterns was selected as the study area.Different rule sets involving spectral, spatial and geometric characteristics were developed to beused for object based classification of 2.5 m resolution Spot-5 satellite images to automaticallycreate urban map of the region. Twenty different land cover/use classes obtained from EuropeanUrban Atlas project were applied and an automatic classification approach was suggested for highresolution urban map creation and updating. Integration of different types of data into theclassification decision tree increased the performance and accuracy of the suggested approach. Theaccuracy assessment results illustrated that with the usage of newly proposed rule set algorithms inobject-based classification, urban areas represented with seventeen different sub-classes could bemapped with 94 % or higher overall accuracy.
