Under the Skin - Determining Electrical Appliances from Surface 3D Scans

Ulrich Krispel, Martin Tamke, Torsten Ullrich

Research output: Contribution to conferencePaperResearchpeer-review

Abstract

New computational methods provide means to deduce semantic information from
measurements, such as range scans and photographs of building interiors. In this paper, we
showcase a method that allows to estimate elements that are not directly observable – ducts
and power lines in walls. For this, we combine information, which is deducted by algorithms
from the raw data, with implicit information that is publicly available: technical standards that
restrict the placement of powerlines. These requirements define preferred installation zones,
which are represented by a rule‐based system in the proposed approach.
The approach is structured into the following steps: First, a coarse geometry is extracted from
input measurements; i.e. the unstructured, laser‐scanned point cloud is transformed into a
simplistic building model. Then, visible endpoints of electrical appliances (e.g. sockets,
switches) are detected from picture information using machine learning techniques and a pre-trained classifier. Afterwards, the positions of installation zones in walls are generated using the rule‐based system mentioned above. Finally, a hypothesis of non‐visible cable ducts is generated, under the assumption that (i) the real configuration obeys the rules of legal requirements and standards and (ii) the configuration connects all endpoints using as little as possible resources, i.e. cable length. Results of a first automatic pipeline are discussed.
Original languageEnglish
Pages77-84
Number of pages8
Publication statusPublished - Apr 2016
EventPlaces and Technologies 2016 - University of Belgrade - Faculty of Architecture, Belgrade, Serbia
Duration: 14 Apr 201615 Apr 2016

Conference

ConferencePlaces and Technologies 2016
CountrySerbia
CityBelgrade
Period14/04/1615/04/16

    Fingerprint

Keywords

  • builiding information modeling
  • as-built BIM
  • semantic enrichment
  • geometric enrichment

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Fields of Expertise

  • Information, Communication & Computing

Cite this

Krispel, U., Tamke, M., & Ullrich, T. (2016). Under the Skin - Determining Electrical Appliances from Surface 3D Scans. 77-84. Paper presented at Places and Technologies 2016, Belgrade, Serbia.