Automatic Generation of Building Models with Levels of Detail 1-3
Collection editors:
International Society for Photogrammetry and Remote Sensing (ISPRS)
Title of conference publication:
XXIII ISPRS Congress, Commission III, 12-19 July 2016, Prague, Czech Republic
Journal:
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Issue:
XLI-B-3
Organizer (entity):
International Society for Photogrammetry and Remote Sensing (ISPRS)
Conference title:
International Society for Photogrammetry and Remote Sensing Congress (23., 2016, Prag)
Venue:
Prag
Year of conference:
2016
Date of conference beginning:
12.07.2016
Date of conference ending:
19.07.2016
Publishing institution:
International Society for Photogrammetry and Remote Sensing (ISPRS)
Year:
2016
Pages from - to:
649-654
Language:
Englisch
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. «
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 mod... »