TY - JOUR
T1 - Extracting Buildings from Aerial Images Using Hierarchical Aggregation in 2D and 3D
AU - Fischer, André
AU - Kolbe, Thomas H.
AU - Lang, Felicitas
AU - Cremers, Armin B.
AU - Förstner, Wolfgang
AU - Plümer, Lutz
AU - Steinhage, Volker
N1 - Funding Information:
This work was largely done within the the project “Semantic Modeling and Extraction of Spatial Objects from Images and Maps” especially in the subproject “Building Extraction” which is supported by the Deutsche Forschungsgemein-schaft, DFG. We thank the DFG for supporting our work.
PY - 1998/11
Y1 - 1998/11
N2 - We propose a model-based approach to automated 3D extraction of buildings from aerial images. We focus on a reconstruction strategy that is not restricted to a small class of buildings. Therefore, we employ a generic modeling approach which relies on the well-defined combination of building part models. Building parts are classified by their roof type. Starting from low-level image features we combine data-driven and model-driven processes within a multilevel aggregation hierarchy, thereby using a tight coupling of 2D image and 3D object modeling and processing, ending up in complex 3D building estimations of shape and location. Due to the explicit representation of well-defined processing states in terms of model-based 2D and 3D descriptions at all levels of modeling and data aggregation, our approach reveals a great potential for reliable building extraction.
AB - We propose a model-based approach to automated 3D extraction of buildings from aerial images. We focus on a reconstruction strategy that is not restricted to a small class of buildings. Therefore, we employ a generic modeling approach which relies on the well-defined combination of building part models. Building parts are classified by their roof type. Starting from low-level image features we combine data-driven and model-driven processes within a multilevel aggregation hierarchy, thereby using a tight coupling of 2D image and 3D object modeling and processing, ending up in complex 3D building estimations of shape and location. Due to the explicit representation of well-defined processing states in terms of model-based 2D and 3D descriptions at all levels of modeling and data aggregation, our approach reveals a great potential for reliable building extraction.
KW - Aspect hierarchies, constraint logic programming
KW - Building modeling
KW - Coupling of 2D and 3D modeling
KW - Explicit 2D modeling
KW - Midlevel feature aggregates
KW - Multiimage correspondence analysis
KW - Multilayer aggregation
UR - http://www.scopus.com/inward/record.url?scp=0032209064&partnerID=8YFLogxK
U2 - 10.1006/cviu.1998.0721
DO - 10.1006/cviu.1998.0721
M3 - Article
AN - SCOPUS:0032209064
SN - 1077-3142
VL - 72
SP - 185
EP - 203
JO - Computer Vision and Image Understanding
JF - Computer Vision and Image Understanding
IS - 2
ER -