In this paper, an algorithm is proposed for automatically generating three-dimensional (3D) building models in dense urban areas. The proposed algorithm uses the results of building segmentation from aerial photographs. After airborne light detection and ranging (LiDAR) data are filtered, point clouds are classified into small groups, and the principal azimuthal directions are determined. Normals to the roofs of the buildings are then determined in order to keep consistency with the direction of the group of roofs. By considering the segmented regions and the normals, models of actual building types-gable-roof, hip-roof, flat-roof and slant-roof buildings-are generated. The proposed algorithm is applied to Higashiyama ward, Kyoto, Japan. Owing to the information of building regions provided by segmentation, the modeling is successful even in dense urban areas. Therefore, the proposed algorithm is concluded to be effective in automatically generating building models in dense urban areas.
[1]
Junichi Susaki.
Segmentation of Shadowed Buildings in Dense Urban Areas from Aerial Photographs
,
2012,
Remote. Sens..
[2]
C. Fraser,et al.
Automatic Detection of Residential Buildings Using LIDAR Data and Multispectral Imagery
,
2010
.
[3]
Horst Steuer.
Height snakes: 3D building reconstruction from aerial image and laser scanner data
,
2011,
2011 Joint Urban Remote Sensing Event.
[4]
K.C. Slatton,et al.
Improved Classification of Building Infrastructure from Airborne Lidar Data Using Spin Images and Fusion with Ground-Based Lidar
,
2007,
2007 Urban Remote Sensing Joint Event.
[5]
S. J. Oude Elberink,et al.
Target graph matching for building reconstruction
,
2009
.
[6]
Demetri Terzopoulos,et al.
Snakes: Active contour models
,
2004,
International Journal of Computer Vision.