Formalising Expert Knowledge for Building Information Models: Automated Identification of Electrical Wiring from 3D Scans

Research output: Chapter in Book/Report/Conference proceedingChapterResearchpeer-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 explicit information, which is deduced by algorithms from measured data, with implicit information that is publicly available: technical standards that restrict the placement of electrical power lines. We present a complete pipeline from measurements to a hypothesis of these power lines within walls. The approach is structured into the following steps: First, a coarse geometry is extracted from input measurements; i.e., the unstructured point cloud which was acquired by laser scanning is transformed into a simplistic building model. Then, visible endpoints of electrical appliances (e.g. sockets, switches) are detected from photos using machine learning techniques and a pre-trained classifier. Afterwards, positions of installation zones in walls are generated. 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 a minimal amount of resources, i.e. cable length.
Original languageEnglish
Title of host publicationKeeping Up with Technologies to Create the Cognitive City
EditorsEva Vaništa Lazarević, Milena Vukmirović, Aleksandra Krstić-Furundžić, Aleksandra Đukić
Place of PublicationUK
PublisherCambridge Scholars Publishing
Chapter23
Pages318-328
Number of pages11
ISBN (Print)978-1-5275-2048-6
Publication statusPublished - 2019
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

Electric wiring
Identification (control systems)
Electric conduits
Computational methods
Ducts
Learning systems
Cables
Classifiers
Pipelines
Semantics
Switches
Scanning
Geometry
Lasers

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications

Fields of Expertise

  • Information, Communication & Computing

Cite this

Krispel, U., Ullrich, T., & Tamke, M. (2019). Formalising Expert Knowledge for Building Information Models: Automated Identification of Electrical Wiring from 3D Scans. In E. V. Lazarević, M. Vukmirović, A. Krstić-Furundžić, & A. Đukić (Eds.), Keeping Up with Technologies to Create the Cognitive City (pp. 318-328). UK: Cambridge Scholars Publishing.

Formalising Expert Knowledge for Building Information Models: Automated Identification of Electrical Wiring from 3D Scans. / Krispel, Ulrich; Ullrich, Torsten; Tamke, Martin.

Keeping Up with Technologies to Create the Cognitive City. ed. / Eva Vaništa Lazarević; Milena Vukmirović; Aleksandra Krstić-Furundžić; Aleksandra Đukić. UK : Cambridge Scholars Publishing, 2019. p. 318-328.

Research output: Chapter in Book/Report/Conference proceedingChapterResearchpeer-review

Krispel, U, Ullrich, T & Tamke, M 2019, Formalising Expert Knowledge for Building Information Models: Automated Identification of Electrical Wiring from 3D Scans. in EV Lazarević, M Vukmirović, A Krstić-Furundžić & A Đukić (eds), Keeping Up with Technologies to Create the Cognitive City. Cambridge Scholars Publishing, UK, pp. 318-328, Places and Technologies 2016, Belgrade, Serbia, 14/04/16.
Krispel U, Ullrich T, Tamke M. Formalising Expert Knowledge for Building Information Models: Automated Identification of Electrical Wiring from 3D Scans. In Lazarević EV, Vukmirović M, Krstić-Furundžić A, Đukić A, editors, Keeping Up with Technologies to Create the Cognitive City. UK: Cambridge Scholars Publishing. 2019. p. 318-328
Krispel, Ulrich ; Ullrich, Torsten ; Tamke, Martin. / Formalising Expert Knowledge for Building Information Models: Automated Identification of Electrical Wiring from 3D Scans. Keeping Up with Technologies to Create the Cognitive City. editor / Eva Vaništa Lazarević ; Milena Vukmirović ; Aleksandra Krstić-Furundžić ; Aleksandra Đukić. UK : Cambridge Scholars Publishing, 2019. pp. 318-328
@inbook{e0cc4a2a19be4ed48fd0cf4722c9fd4f,
title = "Formalising Expert Knowledge for Building Information Models: Automated Identification of Electrical Wiring from 3D Scans",
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 explicit information, which is deduced by algorithms from measured data, with implicit information that is publicly available: technical standards that restrict the placement of electrical power lines. We present a complete pipeline from measurements to a hypothesis of these power lines within walls. The approach is structured into the following steps: First, a coarse geometry is extracted from input measurements; i.e., the unstructured point cloud which was acquired by laser scanning is transformed into a simplistic building model. Then, visible endpoints of electrical appliances (e.g. sockets, switches) are detected from photos using machine learning techniques and a pre-trained classifier. Afterwards, positions of installation zones in walls are generated. 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 a minimal amount of resources, i.e. cable length.",
author = "Ulrich Krispel and Torsten Ullrich and Martin Tamke",
year = "2019",
language = "English",
isbn = "978-1-5275-2048-6",
pages = "318--328",
editor = "Lazarević, {Eva Vaništa} and Milena Vukmirović and Aleksandra Krstić-Furundžić and Aleksandra Đukić",
booktitle = "Keeping Up with Technologies to Create the Cognitive City",
publisher = "Cambridge Scholars Publishing",

}

TY - CHAP

T1 - Formalising Expert Knowledge for Building Information Models: Automated Identification of Electrical Wiring from 3D Scans

AU - Krispel, Ulrich

AU - Ullrich, Torsten

AU - Tamke, Martin

PY - 2019

Y1 - 2019

N2 - 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 explicit information, which is deduced by algorithms from measured data, with implicit information that is publicly available: technical standards that restrict the placement of electrical power lines. We present a complete pipeline from measurements to a hypothesis of these power lines within walls. The approach is structured into the following steps: First, a coarse geometry is extracted from input measurements; i.e., the unstructured point cloud which was acquired by laser scanning is transformed into a simplistic building model. Then, visible endpoints of electrical appliances (e.g. sockets, switches) are detected from photos using machine learning techniques and a pre-trained classifier. Afterwards, positions of installation zones in walls are generated. 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 a minimal amount of resources, i.e. cable length.

AB - 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 explicit information, which is deduced by algorithms from measured data, with implicit information that is publicly available: technical standards that restrict the placement of electrical power lines. We present a complete pipeline from measurements to a hypothesis of these power lines within walls. The approach is structured into the following steps: First, a coarse geometry is extracted from input measurements; i.e., the unstructured point cloud which was acquired by laser scanning is transformed into a simplistic building model. Then, visible endpoints of electrical appliances (e.g. sockets, switches) are detected from photos using machine learning techniques and a pre-trained classifier. Afterwards, positions of installation zones in walls are generated. 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 a minimal amount of resources, i.e. cable length.

UR - https://www.cambridgescholars.com/keeping-up-with-technologies-to-create-the-cognitive-city

M3 - Chapter

SN - 978-1-5275-2048-6

SP - 318

EP - 328

BT - Keeping Up with Technologies to Create the Cognitive City

A2 - Lazarević, Eva Vaništa

A2 - Vukmirović, Milena

A2 - Krstić-Furundžić, Aleksandra

A2 - Đukić, Aleksandra

PB - Cambridge Scholars Publishing

CY - UK

ER -