期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2007
卷号：XXXVI-1/W51
出版社：Copernicus Publications
摘要：Green areas are important parts of urban sprawl with environmental and social effects. Mapping of urban green is a basic condition for effective management and protection. Fast growing of settlements and rising of ecological problems in urban zones lead to larger use of advanced technologies of Remote Sensing to acquire detailed and accurate information about land use for management and planning. Remote Sensing data and its software processing represents powerful tool for creation of thematic maps. There are several satellites which provide image data. Ikonos and QuickBird images are included among data with very high resolution (VHR). Each of them has different characteristics; above all it is spatial resolution. There are two basic ways how image processing software treats the images: per pixel and object oriented approaches. This paper is focused on comparison of different classification techniques used on various satellite images and oriented to map vegetation. Subsets of both scenes were chosen for the analyses. Area of interest displays Brno city quarter Lesná (CZ) as it represents typical residential quarter with single houses, blocks of flats and large green areas.
