Volume XLI-B3
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B3, 649-654, 2016
https://doi.org/10.5194/isprs-archives-XLI-B3-649-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B3, 649-654, 2016
https://doi.org/10.5194/isprs-archives-XLI-B3-649-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.

  10 Jun 2016

10 Jun 2016

AUTOMATIC GENERATION OF BUILDING MODELS WITH LEVELS OF DETAIL 1-3

W. Nguatem1, M. Drauschke1,2, and H. Mayer1 W. Nguatem et al.
  • 1Bundeswehr University Munich, Institute for Applied Computer Science, Visual Computing, Neubiberg, Germany
  • 2German Aerospace Center, Institute of Robotics and Mechatronics, Perception and Cognition, Oberpfaffenhofen, Germany

Keywords: Building Model, Orientation, 3D Reconstruction, Point Cloud, Segmentation

Abstract. We present a workflow for the automatic generation of building models with levels of detail (LOD) 1 to 3 according to the CityGML standard (Gröger et al., 2012). We start with orienting unsorted image sets employing (Mayer et al., 2012), we compute depth maps using semi-global matching (SGM) (Hirschmüller, 2008), and fuse these depth maps to reconstruct dense 3D point clouds (Kuhn et al., 2014). Based on planes segmented from these point clouds, we have developed a stochastic method for roof model selection (Nguatem et al., 2013) and window model selection (Nguatem et al., 2014). We demonstrate our workflow up to the export into CityGML.