Object-oriented mapping and analysis of urban land use/cover using IKONOS data

There are a number of challenges in applying high-spatial resolution satellite image data for analysis of larger urban areas. This paper explores the use of object-oriented image analysis approaches in mapping urban land cover and land use. The study is based on seven IKONOS images covering the Santa Barbara, CA region. Image processing included geometric and atmospheric correction and image segmentation and classification using spectral and spatial information to separate 9 land cover classes 79 % overall accuracy was achieved with this approach. Specific problems are identified due the spectral and spatial complexity of urban areas, causing confusion between different roof types, roads and bare soil and NPV. Further analysis and refinement of the land cover mapping product (in particular buildings) applied two spatial metrics urban land use and socioeconomic information. The results show the importance, capabilities and challenges of object-oriented approaches in providing detailed and accurate information about the physical structure of urban areas and their relationship to urban land use and socioeconomic characteristics that should be further investigated in related studies.