- DOI: 10.1049/cp.2011.0282
- ISBN: 978-1-84919-326-9
- Location: Shanghai, China
- Conference date: 6-8 July 2011
- Format: PDF
Remote sensing technology can obtain the urban land cover information quickly and accurately, and it has been widely used in the urban development. In view of the information extraction present in high resolution remote sensing image and database construction characteristics, in this paper, the Google Earth image is data source, an object-oriented method including image segmentation, feature space optimization and the fuzzy classification rules are proposed to extract the urban land-cover information. The precision of the extraction information is 94.17% and Kappa coefficient is 0.8302. The format of urban land-cover information was changed from raster to vector, then which was transferred to GIS software to construct the database. The results show that it has proved the feasibility and practicability to extract the urban land cover information from the high resolution remote sensing images and construct database in the GIS software. (7 pages)
Inspec keywords: geophysical image processing; image resolution; feature extraction; geographic information systems; image segmentation; optimisation; visual databases; image classification; fuzzy set theory; land use planning; remote sensing; object-oriented methods
Subjects: Combinatorial mathematics; Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research; Optical, image and video signal processing; Computer vision and image processing techniques; Geography and cartography computing; Public administration; Combinatorial mathematics; Spatial and pictorial databases; Other topics in Earth sciences
Related content
content/conferences/10.1049/cp.2011.0282
pub_keyword,iet_inspecKeyword,pub_concept
6
6
