3D posture estimation from 2D posture data for construction workers

Y. Yu; H. Li; X. Yang

3D posture estimation from 2D posture data for construction workers

Y. Yu, H. Li, X. Yang

Research output: Unpublished conference presentation (presented paper, abstract, poster) › Conference presentation (not published in journal/proceeding/book) › Academic research › peer-review

2 Citations (Scopus)

Abstract

Construction workers’ behaviour is important for safety, health and productivity management. Workers’ 3D postures are the data foundation of their behaviours. This paper established a preliminary 3D posture dataset of construction tasks and provided a 3D posture estimation method based on 2D joint locations. The results showed that the method could estimate 3D postures accurately and timely. The mean joint error and estimation time of each frame were 1.10 cm and 0.12 ms respectively. This method makes it possible to estimate construction workers’ 3D postures from construction site images and contributes to a data-based construction workers’ behaviour management.

Original language	English
Pages	26-34
Number of pages	9
Publication status	Published - 2019
Event	36th International Symposium on Automation and Robotics in Construction, ISARC 2019 - Banff, Canada Duration: 21 May 2019 → 24 May 2019

Conference

Conference	36th International Symposium on Automation and Robotics in Construction, ISARC 2019
Country/Territory	Canada
City	Banff
Period	21/05/19 → 24/05/19

Keywords

Behavior management
Construction worker
Posture estimation

ASJC Scopus subject areas

Artificial Intelligence
Building and Construction
Human-Computer Interaction

Cite this

@conference{b6bc9b24a93b43e0bec760c51d2b8fc1,

title = "3D posture estimation from 2D posture data for construction workers",

abstract = "Construction workers{\textquoteright} behaviour is important for safety, health and productivity management. Workers{\textquoteright} 3D postures are the data foundation of their behaviours. This paper established a preliminary 3D posture dataset of construction tasks and provided a 3D posture estimation method based on 2D joint locations. The results showed that the method could estimate 3D postures accurately and timely. The mean joint error and estimation time of each frame were 1.10 cm and 0.12 ms respectively. This method makes it possible to estimate construction workers{\textquoteright} 3D postures from construction site images and contributes to a data-based construction workers{\textquoteright} behaviour management.",

keywords = "Behavior management, Construction worker, Posture estimation",

author = "Y. Yu and H. Li and X. Yang",

note = "Publisher Copyright: {\textcopyright} 2019 International Association for Automation and Robotics in Construction I.A.A.R.C. All rights reserved.; 36th International Symposium on Automation and Robotics in Construction, ISARC 2019 ; Conference date: 21-05-2019 Through 24-05-2019",

year = "2019",

language = "English",

pages = "26--34",

}

3D posture estimation from 2D posture data for construction workers. / Yu, Y.; Li, H.; Yang, X.
2019. 26-34 Paper presented at 36th International Symposium on Automation and Robotics in Construction, ISARC 2019, Banff, Canada.

Research output: Unpublished conference presentation (presented paper, abstract, poster) › Conference presentation (not published in journal/proceeding/book) › Academic research › peer-review

TY - CONF

T1 - 3D posture estimation from 2D posture data for construction workers

AU - Yu, Y.

AU - Li, H.

AU - Yang, X.

PY - 2019

Y1 - 2019

N2 - Construction workers’ behaviour is important for safety, health and productivity management. Workers’ 3D postures are the data foundation of their behaviours. This paper established a preliminary 3D posture dataset of construction tasks and provided a 3D posture estimation method based on 2D joint locations. The results showed that the method could estimate 3D postures accurately and timely. The mean joint error and estimation time of each frame were 1.10 cm and 0.12 ms respectively. This method makes it possible to estimate construction workers’ 3D postures from construction site images and contributes to a data-based construction workers’ behaviour management.

AB - Construction workers’ behaviour is important for safety, health and productivity management. Workers’ 3D postures are the data foundation of their behaviours. This paper established a preliminary 3D posture dataset of construction tasks and provided a 3D posture estimation method based on 2D joint locations. The results showed that the method could estimate 3D postures accurately and timely. The mean joint error and estimation time of each frame were 1.10 cm and 0.12 ms respectively. This method makes it possible to estimate construction workers’ 3D postures from construction site images and contributes to a data-based construction workers’ behaviour management.

KW - Behavior management

KW - Construction worker

KW - Posture estimation

UR - http://www.scopus.com/inward/record.url?scp=85071420212&partnerID=8YFLogxK

M3 - Conference presentation (not published in journal/proceeding/book)

AN - SCOPUS:85071420212

SP - 26

EP - 34

T2 - 36th International Symposium on Automation and Robotics in Construction, ISARC 2019

Y2 - 21 May 2019 through 24 May 2019

ER -

3D posture estimation from 2D posture data for construction workers

Abstract

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this