期刊名称：American Journal of Geographic Information System
印刷版ISSN：2163-1131
电子版ISSN：2163-114X
出版年度：2013
卷号：2
期号：3
页码：27-36
DOI：10.5923/j.ajgis.20130203.01
语种：English
出版社：Scientific & Academic Publishing Co.
摘要：The aim of this study is to compare the changes that occurred in the main urban land cover classes of Ulaanbaatar, the capital city of Mongolia during centralized economy (i.e. 1969-1990) with the changes occurred during market-based economy (i.e. 1990-2011) and describe the socio-economic reasons for the changes. For the analysis, multitemporal high resolution optical and microwave remote sensing (RS) images as well as geographical information system (GIS) and census data sets are used. To extract the reliable urban land cover information from the available RS data sets, a refined maximum likelihood classification (MLC) algorithm that uses spatial thresholds defined from the contextual knowledge is constructed. Before applying the classification decision rule, some ordinary and advanced image fusion techniques are applied to the selected RS data sets, in order to define the most efficient fusion method that can create the best color image to be used for training sample selection as well as for defining the contextual knowledge. Overall, the analysis indicates that during the periods of both centralized and market-based economies the most significant change occurs in the ger area of Ulaanbaatar city and the main reason for this is the growing population and shortage of modern accommodation.
关键词：Urban Land Cover; Change Analysis; RS; GIS; Classification
