On-Demand Monitoring of Construction Projects through a Game-Like Hybrid Application of BIM and Machine Learning

Farzad Rahimian, Saleh Seyedzadeh, Stephen Oliver, Sergio Rodriguez, Nashwan Dawood

Research output: Contribution to journalArticle

Abstract

Whilst unavoidable, inspections, progress monitoring, and comparing as-planned with as-built conditions in construction projects do not readily add tangible intrinsic value to the end-users. In large-scale construction projects, the process of monitoring the implementation of every single part of build-ings and reflecting them on the BIM models can become highly labour in-tensive and error-prone, due to the vast amount of data produced in the form of schedules, reports and photo logs. In order to address the men-tioned methodological and technical gap, this paper presents a framework and a proof of concept prototype for on-demand automated simulation of con-struction projects, integrating some cutting edge IT solutions, namely image processing, machine learning, BIM and Virtual Reality. This study utilised the Unity game engine to integrate data from the original BIM models and the as-built images, which were processed via various computer vision tech-niques. These methods include object recognition and semantic segmenta-tion for identifying different structural elements through supervised training in order to superimpose the real world images on the as-planned model. The proposed framework leads to an automated update of the 3D virtual environ-ment with states of the construction site. This framework empowers project managers and stockholders with an advanced decision-making tool, high-lighting the inconsistencies in an effective manner. This paper contributes to body knowledge by providing a technical exemplar for the integration of ML and image processing approaches with immersive and interactive BIM interfaces, the algorithms and program codes of which can help replicability of these approaches by other scholars.
Original languageEnglish
Article number103012
Number of pages14
JournalAutomation in Construction
Volume110
Early online date27 Nov 2019
DOIs
Publication statusE-pub ahead of print - 27 Nov 2019

Fingerprint

Learning systems
Monitoring
Image processing
Object recognition
Virtual reality
Computer vision
Managers
Lighting
Inspection
Decision making
Semantics
Personnel
Engines

Cite this

@article{3abc024644e644419ca3c557b8bb6ce6,
title = "On-Demand Monitoring of Construction Projects through a Game-Like Hybrid Application of BIM and Machine Learning",
abstract = "Whilst unavoidable, inspections, progress monitoring, and comparing as-planned with as-built conditions in construction projects do not readily add tangible intrinsic value to the end-users. In large-scale construction projects, the process of monitoring the implementation of every single part of build-ings and reflecting them on the BIM models can become highly labour in-tensive and error-prone, due to the vast amount of data produced in the form of schedules, reports and photo logs. In order to address the men-tioned methodological and technical gap, this paper presents a framework and a proof of concept prototype for on-demand automated simulation of con-struction projects, integrating some cutting edge IT solutions, namely image processing, machine learning, BIM and Virtual Reality. This study utilised the Unity game engine to integrate data from the original BIM models and the as-built images, which were processed via various computer vision tech-niques. These methods include object recognition and semantic segmenta-tion for identifying different structural elements through supervised training in order to superimpose the real world images on the as-planned model. The proposed framework leads to an automated update of the 3D virtual environ-ment with states of the construction site. This framework empowers project managers and stockholders with an advanced decision-making tool, high-lighting the inconsistencies in an effective manner. This paper contributes to body knowledge by providing a technical exemplar for the integration of ML and image processing approaches with immersive and interactive BIM interfaces, the algorithms and program codes of which can help replicability of these approaches by other scholars.",
author = "Farzad Rahimian and Saleh Seyedzadeh and Stephen Oliver and Sergio Rodriguez and Nashwan Dawood",
year = "2019",
month = "11",
day = "27",
doi = "10.1016/j.autcon.2019.103012",
language = "English",
volume = "110",
journal = "Automation in Construction",
issn = "0926-5805",
publisher = "Elsevier",

}

On-Demand Monitoring of Construction Projects through a Game-Like Hybrid Application of BIM and Machine Learning. / Rahimian, Farzad; Seyedzadeh, Saleh; Oliver, Stephen; Rodriguez, Sergio; Dawood, Nashwan.

In: Automation in Construction, Vol. 110, 103012, 29.02.2020.

Research output: Contribution to journalArticle

TY - JOUR

T1 - On-Demand Monitoring of Construction Projects through a Game-Like Hybrid Application of BIM and Machine Learning

AU - Rahimian, Farzad

AU - Seyedzadeh, Saleh

AU - Oliver, Stephen

AU - Rodriguez, Sergio

AU - Dawood, Nashwan

PY - 2019/11/27

Y1 - 2019/11/27

N2 - Whilst unavoidable, inspections, progress monitoring, and comparing as-planned with as-built conditions in construction projects do not readily add tangible intrinsic value to the end-users. In large-scale construction projects, the process of monitoring the implementation of every single part of build-ings and reflecting them on the BIM models can become highly labour in-tensive and error-prone, due to the vast amount of data produced in the form of schedules, reports and photo logs. In order to address the men-tioned methodological and technical gap, this paper presents a framework and a proof of concept prototype for on-demand automated simulation of con-struction projects, integrating some cutting edge IT solutions, namely image processing, machine learning, BIM and Virtual Reality. This study utilised the Unity game engine to integrate data from the original BIM models and the as-built images, which were processed via various computer vision tech-niques. These methods include object recognition and semantic segmenta-tion for identifying different structural elements through supervised training in order to superimpose the real world images on the as-planned model. The proposed framework leads to an automated update of the 3D virtual environ-ment with states of the construction site. This framework empowers project managers and stockholders with an advanced decision-making tool, high-lighting the inconsistencies in an effective manner. This paper contributes to body knowledge by providing a technical exemplar for the integration of ML and image processing approaches with immersive and interactive BIM interfaces, the algorithms and program codes of which can help replicability of these approaches by other scholars.

AB - Whilst unavoidable, inspections, progress monitoring, and comparing as-planned with as-built conditions in construction projects do not readily add tangible intrinsic value to the end-users. In large-scale construction projects, the process of monitoring the implementation of every single part of build-ings and reflecting them on the BIM models can become highly labour in-tensive and error-prone, due to the vast amount of data produced in the form of schedules, reports and photo logs. In order to address the men-tioned methodological and technical gap, this paper presents a framework and a proof of concept prototype for on-demand automated simulation of con-struction projects, integrating some cutting edge IT solutions, namely image processing, machine learning, BIM and Virtual Reality. This study utilised the Unity game engine to integrate data from the original BIM models and the as-built images, which were processed via various computer vision tech-niques. These methods include object recognition and semantic segmenta-tion for identifying different structural elements through supervised training in order to superimpose the real world images on the as-planned model. The proposed framework leads to an automated update of the 3D virtual environ-ment with states of the construction site. This framework empowers project managers and stockholders with an advanced decision-making tool, high-lighting the inconsistencies in an effective manner. This paper contributes to body knowledge by providing a technical exemplar for the integration of ML and image processing approaches with immersive and interactive BIM interfaces, the algorithms and program codes of which can help replicability of these approaches by other scholars.

U2 - 10.1016/j.autcon.2019.103012

DO - 10.1016/j.autcon.2019.103012

M3 - Article

VL - 110

JO - Automation in Construction

JF - Automation in Construction

SN - 0926-5805

M1 - 103012

ER -