With the availability of large digital frame cameras like the UltraCamX (UCX) additional benefits through a combination
of high-resolution multispectral aerial images with highly accurate digital surface models emerge. This ongoing study
examines the level of detail of urban information that can be extracted. High resolution and the unprecedented geometric
accuracy of the multispectral and the 2.5D object information enable the derivation of detailed and characteristic object
features. The method of object-based classification is not only used to extract meaningful objects, even more important is
a detailed assessment of semantic relationships. Our study shows the explicit advantage of high geometric resolution to
increase the stability of classification and the number of classes in a representative area of Berlin.
In the context of rapid expansion of many cities to enormous agglomerations with high population density and a worldwide
urbanization process serious impacts on environment in urban areas evolve. There is a high demand for the
development and application of efficient methods to analyze and monitor changes in urban areas, to support the planning
decisions in these regions and for security and risk assessment. Efficient, accurate and reliable extraction of buildings
and roof surfaces and their inventory in geographic information systems plays a major role in this context.
Previous analyses of digital airborne data sets show up that the inventory mapping and assessment of building changes is
only possible on the basis of multi-temporal data sets and digital surface models with high resolution. These analyses
confirm explicitly that both high heterogeneity and diversification of urban regions as well as the availability of data sets
from different camera systems increase the need for automated and transferable extraction methods.
In this context two data sets from different high resolution sensors are used for the development of transferable
extraction rule sets within the object-based classification method in Definiens Developer. The Multifunctional Camera
(MFC3) and the UltraCamD (UCD) data sets not only have diverse geometric but also different radiometric
characteristics. As a study area the centre of Berlin, Germany was selected.
Two approaches to generate comparable results from different data sources are tested. The first step deals with the
generation of statistical parameters and the normalization of the two data sets. The second step addresses the
development and adaptation of the rule set for a robust and universal segmentation and classification process.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.