Deep Learning Machine Vision Solutions for Monitoring Safety Structures to Supplement Building Information Models

Tommi Aihkisalo; Anu Purhonen; Ilkka Niskanen

doi:10.1109/SSE60056.2023.00028

Deep Learning Machine Vision Solutions for Monitoring Safety Structures to Supplement Building Information Models

BA4605 Advanced data spaces

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Abstract

Building Information Models (BIM), provide a static view on building structures on design and construction time. During construction time, the safety structures and their positioning among conditions are vital for the safety of the employees on site. The models usually lack the temporospatial information regarding non-static safety structures as maintaining of such information manually is laborious. Thus, automated and continuous safety structure monitoring is cost-efficient and vital keeping the model up-To-date while improving construction site safety and risk information sharing among the construction related personnel during the project. This paper researches of providing up-To-date and supplementary safety structure information to building models by means of various deep learning-based machine vision solutions. The machine vision tasks consist of deep learning safety related object detection in images, point-clouds, and further instance segmentation to enable safety structure fitness determination by more traditional machine vision means.

Original language	English
Title of host publication	2023 IEEE International Conference on Software Services Engineering, SSE 2023
Editors	Claudio Ardagna, Nimanthi Atukorala, Carl K. Chang, Rong N. Chang, Jing Fan, Geoffrey Fox, Sumi Helal, Zhi Jin, Qinghua Lu, Tiberiu Seceleanu, Stephen S. Yau
Publisher	IEEE Institute of Electrical and Electronic Engineers
Pages	138-147
ISBN (Electronic)	979-8-3503-4075-4
ISBN (Print)	979-8-3503-4076-1
DOIs	https://doi.org/10.1109/SSE60056.2023.00028
Publication status	Published - 2023
MoE publication type	A4 Article in a conference publication
Event	IEEE International Conference on Software Services Engineering, SSE 2023 - Hybrid, Chicago, United States Duration: 2 Jul 2023 → 8 Jul 2023

Conference

Conference	IEEE International Conference on Software Services Engineering, SSE 2023
Country/Territory	United States
City	Chicago
Period	2/07/23 → 8/07/23

Funding

ACKNOWLEDGMENT This research was part of BIMprove project that has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 958450. Authors would also like to thank especially Zurich University of Applied Sciences, HRS Real Estate SA and VIAS S.A for supplying necessary data, images and point clouds, for trials.

Keywords

building information model
computer vision
deep learning
safety structure

Access to Document

10.1109/SSE60056.2023.00028

Cite this

Aihkisalo, T., Purhonen, A., & Niskanen, I. (2023). Deep Learning Machine Vision Solutions for Monitoring Safety Structures to Supplement Building Information Models. In C. Ardagna, N. Atukorala, C. K. Chang, R. N. Chang, J. Fan, G. Fox, S. Helal, Z. Jin, Q. Lu, T. Seceleanu, & S. S. Yau (Eds.), 2023 IEEE International Conference on Software Services Engineering, SSE 2023 (pp. 138-147). IEEE Institute of Electrical and Electronic Engineers. https://doi.org/10.1109/SSE60056.2023.00028

Aihkisalo, Tommi ; Purhonen, Anu ; Niskanen, Ilkka. / Deep Learning Machine Vision Solutions for Monitoring Safety Structures to Supplement Building Information Models. 2023 IEEE International Conference on Software Services Engineering, SSE 2023. editor / Claudio Ardagna ; Nimanthi Atukorala ; Carl K. Chang ; Rong N. Chang ; Jing Fan ; Geoffrey Fox ; Sumi Helal ; Zhi Jin ; Qinghua Lu ; Tiberiu Seceleanu ; Stephen S. Yau. IEEE Institute of Electrical and Electronic Engineers, 2023. pp. 138-147

@inproceedings{296dd1ada7814d46a11877e8454a1448,

title = "Deep Learning Machine Vision Solutions for Monitoring Safety Structures to Supplement Building Information Models",

abstract = "Building Information Models (BIM), provide a static view on building structures on design and construction time. During construction time, the safety structures and their positioning among conditions are vital for the safety of the employees on site. The models usually lack the temporospatial information regarding non-static safety structures as maintaining of such information manually is laborious. Thus, automated and continuous safety structure monitoring is cost-efficient and vital keeping the model up-To-date while improving construction site safety and risk information sharing among the construction related personnel during the project. This paper researches of providing up-To-date and supplementary safety structure information to building models by means of various deep learning-based machine vision solutions. The machine vision tasks consist of deep learning safety related object detection in images, point-clouds, and further instance segmentation to enable safety structure fitness determination by more traditional machine vision means.",

keywords = "building information model, computer vision, deep learning, safety structure",

author = "Tommi Aihkisalo and Anu Purhonen and Ilkka Niskanen",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; IEEE International Conference on Software Services Engineering, SSE 2023 ; Conference date: 02-07-2023 Through 08-07-2023",

year = "2023",

doi = "10.1109/SSE60056.2023.00028",

language = "English",

isbn = "979-8-3503-4076-1",

pages = "138--147",

editor = "Claudio Ardagna and Nimanthi Atukorala and Chang, \{Carl K.\} and Chang, \{Rong N.\} and Jing Fan and Geoffrey Fox and Sumi Helal and Zhi Jin and Qinghua Lu and Tiberiu Seceleanu and Yau, \{Stephen S.\}",

booktitle = "2023 IEEE International Conference on Software Services Engineering, SSE 2023",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

address = "United States",

}

Aihkisalo, T , Purhonen, A & Niskanen, I 2023, Deep Learning Machine Vision Solutions for Monitoring Safety Structures to Supplement Building Information Models. in C Ardagna, N Atukorala, CK Chang, RN Chang, J Fan, G Fox, S Helal, Z Jin, Q Lu, T Seceleanu & SS Yau (eds), 2023 IEEE International Conference on Software Services Engineering, SSE 2023. IEEE Institute of Electrical and Electronic Engineers, pp. 138-147, IEEE International Conference on Software Services Engineering, SSE 2023, Chicago, Illinois, United States, 2/07/23. https://doi.org/10.1109/SSE60056.2023.00028

Deep Learning Machine Vision Solutions for Monitoring Safety Structures to Supplement Building Information Models. / Aihkisalo, Tommi ; Purhonen, Anu ; Niskanen, Ilkka.
2023 IEEE International Conference on Software Services Engineering, SSE 2023. ed. / Claudio Ardagna; Nimanthi Atukorala; Carl K. Chang; Rong N. Chang; Jing Fan; Geoffrey Fox; Sumi Helal; Zhi Jin; Qinghua Lu; Tiberiu Seceleanu; Stephen S. Yau. IEEE Institute of Electrical and Electronic Engineers, 2023. p. 138-147.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Deep Learning Machine Vision Solutions for Monitoring Safety Structures to Supplement Building Information Models

AU - Aihkisalo, Tommi

AU - Purhonen, Anu

AU - Niskanen, Ilkka

PY - 2023

Y1 - 2023

N2 - Building Information Models (BIM), provide a static view on building structures on design and construction time. During construction time, the safety structures and their positioning among conditions are vital for the safety of the employees on site. The models usually lack the temporospatial information regarding non-static safety structures as maintaining of such information manually is laborious. Thus, automated and continuous safety structure monitoring is cost-efficient and vital keeping the model up-To-date while improving construction site safety and risk information sharing among the construction related personnel during the project. This paper researches of providing up-To-date and supplementary safety structure information to building models by means of various deep learning-based machine vision solutions. The machine vision tasks consist of deep learning safety related object detection in images, point-clouds, and further instance segmentation to enable safety structure fitness determination by more traditional machine vision means.

AB - Building Information Models (BIM), provide a static view on building structures on design and construction time. During construction time, the safety structures and their positioning among conditions are vital for the safety of the employees on site. The models usually lack the temporospatial information regarding non-static safety structures as maintaining of such information manually is laborious. Thus, automated and continuous safety structure monitoring is cost-efficient and vital keeping the model up-To-date while improving construction site safety and risk information sharing among the construction related personnel during the project. This paper researches of providing up-To-date and supplementary safety structure information to building models by means of various deep learning-based machine vision solutions. The machine vision tasks consist of deep learning safety related object detection in images, point-clouds, and further instance segmentation to enable safety structure fitness determination by more traditional machine vision means.

KW - building information model

KW - computer vision

KW - deep learning

KW - safety structure

UR - https://www.scopus.com/pages/publications/85173566063

U2 - 10.1109/SSE60056.2023.00028

DO - 10.1109/SSE60056.2023.00028

M3 - Conference article in proceedings

AN - SCOPUS:85173566063

SN - 979-8-3503-4076-1

SP - 138

EP - 147

BT - 2023 IEEE International Conference on Software Services Engineering, SSE 2023

A2 - Ardagna, Claudio

A2 - Atukorala, Nimanthi

A2 - Chang, Carl K.

A2 - Chang, Rong N.

A2 - Fan, Jing

A2 - Fox, Geoffrey

A2 - Helal, Sumi

A2 - Jin, Zhi

A2 - Lu, Qinghua

A2 - Seceleanu, Tiberiu

A2 - Yau, Stephen S.

PB - IEEE Institute of Electrical and Electronic Engineers

T2 - IEEE International Conference on Software Services Engineering, SSE 2023

Y2 - 2 July 2023 through 8 July 2023

ER -

Aihkisalo T , Purhonen A , Niskanen I. Deep Learning Machine Vision Solutions for Monitoring Safety Structures to Supplement Building Information Models. In Ardagna C, Atukorala N, Chang CK, Chang RN, Fan J, Fox G, Helal S, Jin Z, Lu Q, Seceleanu T, Yau SS, editors, 2023 IEEE International Conference on Software Services Engineering, SSE 2023. IEEE Institute of Electrical and Electronic Engineers. 2023. p. 138-147 doi: 10.1109/SSE60056.2023.00028

Deep Learning Machine Vision Solutions for Monitoring Safety Structures to Supplement Building Information Models

Abstract

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this