453 
b. Beijing 2008 
to van- 
earning 
AUTOMATIC BUILDING EXTRACTION FROM HIGH RESOLUTION AERIAL 
IMAGES USING ACTIVE CONTOUR MODEL 
»wledge 
e inter- 
Salman Ahmady, Hamid Ebadi, M.J. Valadan Zouj, Hamid Abrishami Moghaddam 
Photogrammetry, K.N. Toosi university of Technology, Dept of Photogrammetry and Remote Sensing, Tehran, Iran - 
salman.ahmadv(2),email.com 
or con- 
844. 
ABSTRACT: 
:ure de 
ale ran- 
Various governmental organizations need accurate, correct and up to date information for optimization of resource and service 
management. In this issue, geospatial information is very important. Geospatial information as essential part of Geospatial 
Information System (GIS) has important role in performance of civil projects, urban service management. Using conventional 
tom-up 
Weiz- 
surveying methods for producing geospatial data require a lot of cost and time. Thus, utilization of modem methods in production 
and updating of this kind of data is necessary.Photogrammetry and Remote Sensing are methods that produce geospatial data in 
extensive area with acceptable accuracy. In various countries of the world, many researches have been carried out and many 
algorithms have been introduced in order to decrease human operation in automatic feature extraction of satellite images. Building is 
ion for 
;r Aca- 
one of the features that take the maximum of time and cost of feature extraction due to its abundance in urban area. As a result, on 
access to a model or algorithm of automatic or semi-automatic extraction of this feature not only minimizes human role in producing 
large scale maps but also has a dramatic effect on time and cost of the project. The aim of this paper is automatic extraction of 
boundary of this feature from high resolution aerial images in a way that its output is a vector map that needs the least editing in GIS. 
a aerial 
r IU 74, 
the main goal of this research is to introduce a method based on active contour model that the initialization stage of algorithm can be 
carried out automatically and active contour be ultimately optimized in building extraction. A new model is also suggested for 
automatic detection and extraction of boundary of buildings. New model of active contour can detect and extract boundary of 
building very accurately compared to classical model of active contour model and avoid detection of the boundary of features that are 
rimetry. 
in neighbor of buildings such as streets and trees. The result of applying this model shows that the active contour model works better 
than other models of detection and extraction of building boundaries in urban area. 
tem for 
’ Com- 
1. INTRODUCTION information such as Lidar data. Halla et al. (1999) have 
extracted location of buildings from image by using 
ft mar- 
>. 287- 
Photogrammetry and Remote Sensing are methods that produce classification algorithms and height data. Zimmermann et al. 
geospatial data in extensive area with acceptable accuracy. (2000) produced DSM data from stereo images. Then they 
Furthermore, project cost and time of using these methods is detected building's roof model by applying slope and aspect 
lower than other production methods of geospatial information. operators. Also in the (Zhao et al, 2000, Jin et al, 2005) height 
nodels, 
e inter- 
3-178. 
Because of the fact that nowadays, spatial and spectral data and morphological operators have been used for extraction 
resolution of satellite sensors has been improved and high of buildings, 
quality images such as Ikonos and Quickbird are accessed to 
provide needs of civil users, utilization of these images for In some researches, different active contour models such as 
ability. 
providing and updating of maps and geospatial information has Snake model have been employed for building boundary 
been approved all over the world. recognition. In (Peng et al, 2004) a specific Snake model has 
costing 
'achine 
been introduced for building boundaries from aerial images with 
Building is one of the features made by human that takes the a new energy function. The paper of) Mayunga et al, 
maximum of time and cost of feature extraction due to its 2005) proposed a semi automatic algorithm for building 
abundance in urban area. As a result, on access to a model or extraction from Quickbird images. In this paper within the 
algorithm of automatic or semiautomatic extraction of this boundary of each building, a point is selected. Then the initial 
A. and 
íeir lo- 
hina. 
feature not only minimizes human role in producing large scale curves of the model are produced and the accurate boundaries of 
maps but also has a dramatic effect on time and cost of the buildings are detected in the iterative procedure. In the another 
project. Finding such an algorithm can also be efficient in paper (Guo et al, 2002) at first the approximate position of 
automatic extraction of other features similar to buildings. building's boundary is extracted from Lidar data and then Snake 
incom- 
;rspec- 
Model extract precise boundary of each building. 
Because of irregular structure and closeness of buildings in 
>n with 
urban area, the maximum researches in domain of automatic Other researches have been used artificial intelligence such as 
building extraction from high resolution aerial and satellite nero-fuzzy system for recognition and detection buildings from 
images, are done from integration of Lidar data and images other object in aerial and satellite images (Samadzadegan et al, 
(Rottensteiner et al, 2005). For example in the research of (Sohn 2005). 
R. and 
id mi 
ad IW- 
et al, 2007) at first all features that have a certain height from 
earth are recognized. After that by using NDVI index and other in this paper a model has been introduced for building detection 
information, separate the buildings from other features. Then from aerial images using active contour models based on level 
the sharp edges detect and a polygon fits to the close edges as a set formulation, 
building boundary. In other researches such as (Weidner et al, 
1995, Baillard et al, 1999, Schenk et al, 2002, Guo et al, 2002, 
Rottensteiner et al, 2005) the position of buildings have been 2. DESCRIPTION OF ACTIVE CONTOUR MODEL 
detected by integration of aerial and satellite images into height