An Automatic Hypothesis of Electrical Lines from Range Scans and Photographs

Ulrich Krispel, Torsten Ullrich, Henrik Leander Evers, Martin Tamke

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

19 Downloads (Pure)

Abstract

Building information modeling (BIM) with high level of detail and semantic information on buildings throughout their lifetime are getting more and more important for stakeholders in the building domain. Currently, such models are not yet present for the majority of today’s building stock. With increasing speed and precision of laser scans or photogrammetry, geometric data can be acquired at reasonable costs. Unfortunately, these data are unstructured and do not provide high-level semantic information, which stakeholder require for non-trivial workflows. A current research topic are methods to extract non-visible structures from visible geometric entities. This work uses domain specific geometric and semantic constraints to automatically deduce information that is not directly observable in architectural objects: electrical power supply lines. It utilizes as-built BIM data from scans of indoor spaces in order to provide a hypothesis of paths of electrical lines. The system assumes that legal requirements and standards exist for defining the placement of power supply lines. This prior knowledge is formalized in a set of rules, using a 2D shape grammar that yields installation zones for a given room. Observable endpoints (sockets and switches) are detected in indoor scenes of buildings using methods from computer vision. The information from the reconstructed BIM model, as well as the detections and the generated installation zones are combined in a graph that represents all likely paths the power lines could take. Using this graph and a discrete optimization approach, the subgraph is generated that corresponds to a probable hypothesis. Our approach has been tested against synthetic and measured data and shows promising first results. Application possibilities include generation of a probable wiring for as-built / optically acquired building model, or suggesting cable ducts for a building reorganization or during planning of a new building.
Original languageEnglish
Title of host publicationProceedings of the 16th International Conference on Computing in Civil and Building Engineering
EditorsNobuyoshi Yabuki, Koji Makanae
Number of pages8
Place of PublicationOsaka
Publication date2016
Pages815-822
ISBN (Electronic)978-4-9907371-2-2
Publication statusPublished - 2016
Event16th International Conference on Computing in Civil and Building Engineering - Osaka, Japan
Duration: 6 Jul 20168 Jul 2016
http://www.see.eng.osaka-u.ac.jp/seeit/icccbe2016/

Conference

Conference16th International Conference on Computing in Civil and Building Engineering
CountryJapan
CityOsaka
Period06/07/201608/07/2016
Internet address

Keywords

  • BIM
  • as-built BIM
  • semantic enrichment
  • formal grammar

Artistic research

  • No

Cite this

Krispel, U., Ullrich, T., Evers, H. L., & Tamke, M. (2016). An Automatic Hypothesis of Electrical Lines from Range Scans and Photographs. In N. Yabuki, & K. Makanae (Eds.), Proceedings of the 16th International Conference on Computing in Civil and Building Engineering (pp. 815-822). Osaka.
Krispel, Ulrich ; Ullrich, Torsten ; Evers, Henrik Leander ; Tamke, Martin. / An Automatic Hypothesis of Electrical Lines from Range Scans and Photographs. Proceedings of the 16th International Conference on Computing in Civil and Building Engineering. editor / Nobuyoshi Yabuki ; Koji Makanae. Osaka, 2016. pp. 815-822
@inproceedings{0caed177bc704b2a846130b673c39321,
title = "An Automatic Hypothesis of Electrical Lines from Range Scans and Photographs",
abstract = "Building information modeling (BIM) with high level of detail and semantic information on buildings throughout their lifetime are getting more and more important for stakeholders in the building domain. Currently, such models are not yet present for the majority of today’s building stock. With increasing speed and precision of laser scans or photogrammetry, geometric data can be acquired at reasonable costs. Unfortunately, these data are unstructured and do not provide high-level semantic information, which stakeholder require for non-trivial workflows. A current research topic are methods to extract non-visible structures from visible geometric entities. This work uses domain specific geometric and semantic constraints to automatically deduce information that is not directly observable in architectural objects: electrical power supply lines. It utilizes as-built BIM data from scans of indoor spaces in order to provide a hypothesis of paths of electrical lines. The system assumes that legal requirements and standards exist for defining the placement of power supply lines. This prior knowledge is formalized in a set of rules, using a 2D shape grammar that yields installation zones for a given room. Observable endpoints (sockets and switches) are detected in indoor scenes of buildings using methods from computer vision. The information from the reconstructed BIM model, as well as the detections and the generated installation zones are combined in a graph that represents all likely paths the power lines could take. Using this graph and a discrete optimization approach, the subgraph is generated that corresponds to a probable hypothesis. Our approach has been tested against synthetic and measured data and shows promising first results. Application possibilities include generation of a probable wiring for as-built / optically acquired building model, or suggesting cable ducts for a building reorganization or during planning of a new building.",
keywords = "BIM, as-built BIM, semantic enrichment, formal grammar",
author = "Ulrich Krispel and Torsten Ullrich and Evers, {Henrik Leander} and Martin Tamke",
year = "2016",
language = "English",
pages = "815--822",
editor = "Nobuyoshi Yabuki and Koji Makanae",
booktitle = "Proceedings of the 16th International Conference on Computing in Civil and Building Engineering",

}

Krispel, U, Ullrich, T, Evers, HL & Tamke, M 2016, An Automatic Hypothesis of Electrical Lines from Range Scans and Photographs. in N Yabuki & K Makanae (eds), Proceedings of the 16th International Conference on Computing in Civil and Building Engineering. Osaka, pp. 815-822, 16th International Conference on Computing in Civil and Building Engineering, Osaka, Japan, 06/07/2016.

An Automatic Hypothesis of Electrical Lines from Range Scans and Photographs. / Krispel, Ulrich; Ullrich, Torsten; Evers, Henrik Leander; Tamke, Martin.

Proceedings of the 16th International Conference on Computing in Civil and Building Engineering. ed. / Nobuyoshi Yabuki; Koji Makanae. Osaka, 2016. p. 815-822.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - An Automatic Hypothesis of Electrical Lines from Range Scans and Photographs

AU - Krispel, Ulrich

AU - Ullrich, Torsten

AU - Evers, Henrik Leander

AU - Tamke, Martin

PY - 2016

Y1 - 2016

N2 - Building information modeling (BIM) with high level of detail and semantic information on buildings throughout their lifetime are getting more and more important for stakeholders in the building domain. Currently, such models are not yet present for the majority of today’s building stock. With increasing speed and precision of laser scans or photogrammetry, geometric data can be acquired at reasonable costs. Unfortunately, these data are unstructured and do not provide high-level semantic information, which stakeholder require for non-trivial workflows. A current research topic are methods to extract non-visible structures from visible geometric entities. This work uses domain specific geometric and semantic constraints to automatically deduce information that is not directly observable in architectural objects: electrical power supply lines. It utilizes as-built BIM data from scans of indoor spaces in order to provide a hypothesis of paths of electrical lines. The system assumes that legal requirements and standards exist for defining the placement of power supply lines. This prior knowledge is formalized in a set of rules, using a 2D shape grammar that yields installation zones for a given room. Observable endpoints (sockets and switches) are detected in indoor scenes of buildings using methods from computer vision. The information from the reconstructed BIM model, as well as the detections and the generated installation zones are combined in a graph that represents all likely paths the power lines could take. Using this graph and a discrete optimization approach, the subgraph is generated that corresponds to a probable hypothesis. Our approach has been tested against synthetic and measured data and shows promising first results. Application possibilities include generation of a probable wiring for as-built / optically acquired building model, or suggesting cable ducts for a building reorganization or during planning of a new building.

AB - Building information modeling (BIM) with high level of detail and semantic information on buildings throughout their lifetime are getting more and more important for stakeholders in the building domain. Currently, such models are not yet present for the majority of today’s building stock. With increasing speed and precision of laser scans or photogrammetry, geometric data can be acquired at reasonable costs. Unfortunately, these data are unstructured and do not provide high-level semantic information, which stakeholder require for non-trivial workflows. A current research topic are methods to extract non-visible structures from visible geometric entities. This work uses domain specific geometric and semantic constraints to automatically deduce information that is not directly observable in architectural objects: electrical power supply lines. It utilizes as-built BIM data from scans of indoor spaces in order to provide a hypothesis of paths of electrical lines. The system assumes that legal requirements and standards exist for defining the placement of power supply lines. This prior knowledge is formalized in a set of rules, using a 2D shape grammar that yields installation zones for a given room. Observable endpoints (sockets and switches) are detected in indoor scenes of buildings using methods from computer vision. The information from the reconstructed BIM model, as well as the detections and the generated installation zones are combined in a graph that represents all likely paths the power lines could take. Using this graph and a discrete optimization approach, the subgraph is generated that corresponds to a probable hypothesis. Our approach has been tested against synthetic and measured data and shows promising first results. Application possibilities include generation of a probable wiring for as-built / optically acquired building model, or suggesting cable ducts for a building reorganization or during planning of a new building.

KW - BIM

KW - as-built BIM

KW - semantic enrichment

KW - formal grammar

UR - https://www.researchgate.net/publication/306391889_An_Automatic_Hypothesis_of_Electrical_Lines_from_Range_Scans_and_Photographs

M3 - Article in proceedings

SP - 815

EP - 822

BT - Proceedings of the 16th International Conference on Computing in Civil and Building Engineering

A2 - Yabuki, Nobuyoshi

A2 - Makanae, Koji

CY - Osaka

ER -

Krispel U, Ullrich T, Evers HL, Tamke M. An Automatic Hypothesis of Electrical Lines from Range Scans and Photographs. In Yabuki N, Makanae K, editors, Proceedings of the 16th International Conference on Computing in Civil and Building Engineering. Osaka. 2016. p. 815-822