文章基本信息

标题：Unsupervised Building Extraction from High Resolution Satellite Images Irrespective of Rooftop Structures
本地全文：下载
作者：Mr. Lizy Abraham ; Dr. M.Sasikumar
期刊名称：International Journal of Image Processing (IJIP)
电子版ISSN：1985-2304
出版年度：2012
卷号：6
期号：4
页码：219-232
出版社：Computer Science Journals
摘要：Extraction of geospatial data from the photogrammetric sensing images becomes more and more important with the advances in the technology. Today Geographic Information Systems are used in a large variety of applications in engineering, city planning and social sciences. Geospatial data like roads, buildings and rivers are the most critical feeds of a GIS database. However, extracting buildings is one of the most complex and challenging tasks as there exist a lot of inhomogeneity due to varying hierarchy. The variety of the type of buildings and also the shapes of rooftops are very inconstant. Also in some areas, the buildings are placed irregularly or too close to each other. For these reasons, even by using high resolution IKONOS and QuickBird satellite imagery the quality percentage of building extraction is very less. This paper proposes a solution to the problem of automatic and unsupervised extraction of building features irrespective of rooftop structures in multispectral satellite images. The algorithm instead of detecting the region of interest, eliminates areas other than the region of interest which extract the rooftops completely irrespective of their shapes. Extensive tests indicate that the methodology performs well to extract buildings in complex environments.
关键词：Pan Sharpened Multispectral Image; Rooftop Detection; Otsu's Thresholding; Area Analysis