Abstract
Abstract. Current mobile augmented reality devices are often equipped with range sensors. The Microsoft HoloLens for instance is equipped with a Time-of-Flight (ToF) range camera providing coarse triangle meshes that can be used in custom applications. We suggest to use these triangle meshes for the automatic generation of indoor models that can serve as basis for augmenting their physical counterpart with location-dependent information. In this paper, we present a novel voxel-based approach for automated indoor reconstruction from unstructured three-dimensional geometries like triangle meshes. After an initial voxelisation of the input data, rooms are detected in the resulting voxel grid by segmenting connected voxel components of ceiling candidates and extruding them downwards to find floor candidates. Semantic class labels like ’Wall’, ’Wall Opening’, ’Interior Object’ and ’Empty Interior’ are then assigned to the room voxels in-between ceiling and floor by a rule-based voxel sweep algorithm. Finally, the geometry of the detected walls and their openings is refined in voxel representation. The proposed approach is not restricted to Manhattan World scenarios and does not rely on room surfaces being planar.
Highlights
Current head-worn Augmented Reality (AR) devices like the Microsoft HoloLens1 hold great potential for enriching indoor environments with the in-situ visualisation of location-dependent information, e.g. from digital building information models (Hübner et al, 2018)
We suggest to use these data for the automatic generation of digital models of indoor environments that can serve as basis for augmenting their physical counterpart with location-dependent informative content in an indoor AR setting
While the method is applicable for unstructured 3D data with absolute normals and could be applied to point clouds provided they have normals, we focus in this study on triangle meshes captured with the Microsoft HoloLens
Summary
Current head-worn Augmented Reality (AR) devices like the Microsoft HoloLens hold great potential for enriching indoor environments with the in-situ visualisation of location-dependent information, e.g. from digital building information models (Hübner et al, 2018). While suchlike building models are currently gaining in prevalence with the increasing use of Building Information Modeling (BIM) techniques in the planning and construction stages of building projects (Jung and Lee, 2015), already existing, older buildings frequently lack such a digital representation that could be used in such indoor AR scenarios (Lu and Lee, 2017). Mobile indoor AR devices are often equipped with range sensors to facilitate 1) tracking and relocalisation within indoor environments and 2) convincing placement and interaction of virtual content with the physical surrounding. We suggest to use these data for the automatic generation of digital models of indoor environments that can serve as basis for augmenting their physical counterpart with location-dependent informative content in an indoor AR setting
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
