High Level-of-Detail BIM and Machine Learning for Automated Masonry Wall Defect Surveying

Enrique Valero; Alan Mark Forster; Frédéric Nicolas Bosché; Camille  Renier; Ewan Hyslop; Lyn Wilson

doi:10.22260/ISARC2018/0101

High Level-of-Detail BIM and Machine Learning for Automated Masonry Wall Defect Surveying

Enrique Valero, Alan Mark Forster, Frédéric Nicolas Bosché, Camille Renier, Ewan Hyslop, Lyn Wilson

Research output: Contribution to conference › Paper › peer-review

20 Citations (Scopus)

370 Downloads (Pure)

Abstract

Despite the rapid development of reality capture technologies and progress in data processing techniques, current visual strategies for defect surveying are time consuming manual procedures. These methods often deliver subjective and inaccurate outcomes, leading to inconsistent conclusions for defect classification and ultimately repair needs. In this paper, a strategy for monitoring the evolution of ashlar masonry walls of historic buildings through reality capture, data processing (including machine learning), and (H)BIM models is presented. The proposed method has been tested, at different levels of granularity, in the main façade of the Chapel Royal in Stirling Castle (Scotland), demonstrating its potential.

Original language	English
Pages	740-747
Number of pages	8
DOIs	https://doi.org/10.22260/ISARC2018/0101
Publication status	Published - 20 Jul 2018
Event	35th International Symposium on Automation and Robotics in Construction 2018 - Berlin, Germany Duration: 20 Jul 2018 → 25 Jul 2018 https://isarc2018.blogs.ruhr-uni-bochum.de/

Conference

Conference	35th International Symposium on Automation and Robotics in Construction 2018
Abbreviated title	ISARC 2018
Country/Territory	Germany
City	Berlin
Period	20/07/18 → 25/07/18
Internet address	https://isarc2018.blogs.ruhr-uni-bochum.de/

Access to Document

10.22260/ISARC2018/0101

Download pdfAccepted author manuscript, 1.03 MBLicence: Unspecified

Cite this

@conference{58359a85c448469093e3723ca1a97204,

title = "High Level-of-Detail BIM and Machine Learning for Automated Masonry Wall Defect Surveying",

abstract = "Despite the rapid development of reality capture technologies and progress in data processing techniques, current visual strategies for defect surveying are time consuming manual procedures. These methods often deliver subjective and inaccurate outcomes, leading to inconsistent conclusions for defect classification and ultimately repair needs. In this paper, a strategy for monitoring the evolution of ashlar masonry walls of historic buildings through reality capture, data processing (including machine learning), and (H)BIM models is presented. The proposed method has been tested, at different levels of granularity, in the main fa{\c c}ade of the Chapel Royal in Stirling Castle (Scotland), demonstrating its potential.",

author = "Enrique Valero and Forster, {Alan Mark} and Bosch{\'e}, {Fr{\'e}d{\'e}ric Nicolas} and Camille Renier and Ewan Hyslop and Lyn Wilson",

year = "2018",

month = jul,

day = "20",

doi = "10.22260/ISARC2018/0101",

language = "English",

pages = "740--747",

note = "35th International Symposium on Automation and Robotics in Construction 2018, ISARC 2018 ; Conference date: 20-07-2018 Through 25-07-2018",

url = "https://isarc2018.blogs.ruhr-uni-bochum.de/",

}

TY - CONF

T1 - High Level-of-Detail BIM and Machine Learning for Automated Masonry Wall Defect Surveying

AU - Valero, Enrique

AU - Forster, Alan Mark

AU - Bosché, Frédéric Nicolas

AU - Renier, Camille

AU - Hyslop, Ewan

AU - Wilson, Lyn

PY - 2018/7/20

Y1 - 2018/7/20

N2 - Despite the rapid development of reality capture technologies and progress in data processing techniques, current visual strategies for defect surveying are time consuming manual procedures. These methods often deliver subjective and inaccurate outcomes, leading to inconsistent conclusions for defect classification and ultimately repair needs. In this paper, a strategy for monitoring the evolution of ashlar masonry walls of historic buildings through reality capture, data processing (including machine learning), and (H)BIM models is presented. The proposed method has been tested, at different levels of granularity, in the main façade of the Chapel Royal in Stirling Castle (Scotland), demonstrating its potential.

AB - Despite the rapid development of reality capture technologies and progress in data processing techniques, current visual strategies for defect surveying are time consuming manual procedures. These methods often deliver subjective and inaccurate outcomes, leading to inconsistent conclusions for defect classification and ultimately repair needs. In this paper, a strategy for monitoring the evolution of ashlar masonry walls of historic buildings through reality capture, data processing (including machine learning), and (H)BIM models is presented. The proposed method has been tested, at different levels of granularity, in the main façade of the Chapel Royal in Stirling Castle (Scotland), demonstrating its potential.

U2 - 10.22260/ISARC2018/0101

DO - 10.22260/ISARC2018/0101

M3 - Paper

SP - 740

EP - 747

T2 - 35th International Symposium on Automation and Robotics in Construction 2018

Y2 - 20 July 2018 through 25 July 2018

ER -

High Level-of-Detail BIM and Machine Learning for Automated Masonry Wall Defect Surveying

Abstract

Conference

Access to Document

Fingerprint

Cite this