Automatic urban building boundary extraction from high resolution aerial images using an innovative model of active contours


Nowadays, automatic extraction of man-made objects such as buildings and roads in urban areas has become a topic of growing interest for photogrammetric and computer vision community. Researches in this domain started from late 1980s and used quite different types of source images ranging from single intensity images, color images, laser range images to stereo and multiple images (Peng et al., 2005). Some useful applications are automation information extraction from images and updating geographic information system (GIS) databases. The establishment of the database for urban areas is frequently done by the analysis of aerial imagery since photogrammetric data is three-dimensional, accurate , largely complete and up-to-date. Because manual interpretation is very time consuming, a lot of efforts have been spent to speed up this process by automatic or semi-automatic procedures. A wide range of techniques and algorithms have been proposed for automatically constructing 2D or 3D building models from satellite and aerial imagery. In this field Dash et al. in 2004 used height variation in the context of object periphery data to develop a method based on standard deviation to distinguish between trees and buildings (Dash et al., 2004). Sohn et al. employed Lidar (Light Detection and Ranging) data in 2007 to generate height data for features in an urban region (Sohn and Dowman, 2007). They carried out the following steps for building extraction: first, they identified all features that were a certain height above ground level. Next, using the NDVI index and other information, they distinguished the buildings from other features. Finally, they detected the sharp edges of buildings and matched polygons to the close edges, in order to robustly identify building boundaries (Sohn and Dowman, 2007). In 1999, Halla and co-workers extracted building locations from images using classification algorithms and height data (Halla and Brenner, 1999). Zimmermann et al. in 2000 produced a Digital Surface Model (DSM) data from stereo images. They then used the model to detect building roofs by applying slope and aspect operators (Zimmermann, 2000). Finally, in another study, height data and morphological operators were utilized to extract buildings (Zhao and Trinder, 2000). As reported by Hongjiana and Shiqiang (2006), another approach involves extracting the data and connecting edge pixels. This allows for the derivation of building heights from sparse laser samples and can be used to reconstruct 3D information for each building. Miliaresis and Kokkas (2007) proposed a new method for extracting a class …

DOI: 10.1016/j.jag.2010.02.001

Extracted Key Phrases

11 Figures and Tables

Cite this paper

@article{Ahmadi2010AutomaticUB, title={Automatic urban building boundary extraction from high resolution aerial images using an innovative model of active contours}, author={Salman Ahmadi and Mohammad Javad Valadan Zoej and Hamid Ebadi and Hamid Abrishami Moghaddam and Ali Mohammadzadeh}, journal={Int. J. Applied Earth Observation and Geoinformation}, year={2010}, volume={12}, pages={150-157} }