Analyzing context and productivity of tunnel earthmoving processes using imaging and simulation

Hongjo Kim, Seongdeok Bang, Hoyoung Jeong, Youngjib Ham, Hyoungkwan Kim

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

This study presents an integrated method of construction-process simulation and vision-based context reasoning for productivity analysis of an earthmoving process in a tunnel. Convolutional networks are used to detect construction equipment in the tunnel CCTV video and the context of the earthmoving process is inferred by the context reasoning process. The construction equipment detection model exhibited enhanced performance, with a mean average precision of 99.09%, and the error rate of the estimated context information was only 1.6% of the actual earthmoving context measured by a human. The estimated context information was used as an input for the WebCYCLONE simulation to generate a productivity and cost analysis report. Sensitivity analysis regarding construction equipment provided a new equipment allocation plan that could reduce the cost of the current earthmoving process by 12.25%.

Original languageEnglish
Pages (from-to)188-198
Number of pages11
JournalAutomation in Construction
Volume92
DOIs
Publication statusPublished - 2018 Aug 1

Fingerprint

Construction equipment
Tunnels
Productivity
Imaging techniques
Closed circuit television systems
Sensitivity analysis
Costs

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Civil and Structural Engineering
  • Building and Construction

Cite this

Kim, Hongjo ; Bang, Seongdeok ; Jeong, Hoyoung ; Ham, Youngjib ; Kim, Hyoungkwan. / Analyzing context and productivity of tunnel earthmoving processes using imaging and simulation. In: Automation in Construction. 2018 ; Vol. 92. pp. 188-198.
@article{8e879d5dbc78402e9216644cb334a1f4,
title = "Analyzing context and productivity of tunnel earthmoving processes using imaging and simulation",
abstract = "This study presents an integrated method of construction-process simulation and vision-based context reasoning for productivity analysis of an earthmoving process in a tunnel. Convolutional networks are used to detect construction equipment in the tunnel CCTV video and the context of the earthmoving process is inferred by the context reasoning process. The construction equipment detection model exhibited enhanced performance, with a mean average precision of 99.09{\%}, and the error rate of the estimated context information was only 1.6{\%} of the actual earthmoving context measured by a human. The estimated context information was used as an input for the WebCYCLONE simulation to generate a productivity and cost analysis report. Sensitivity analysis regarding construction equipment provided a new equipment allocation plan that could reduce the cost of the current earthmoving process by 12.25{\%}.",
author = "Hongjo Kim and Seongdeok Bang and Hoyoung Jeong and Youngjib Ham and Hyoungkwan Kim",
year = "2018",
month = "8",
day = "1",
doi = "10.1016/j.autcon.2018.04.002",
language = "English",
volume = "92",
pages = "188--198",
journal = "Automation in Construction",
issn = "0926-5805",
publisher = "Elsevier",

}

Analyzing context and productivity of tunnel earthmoving processes using imaging and simulation. / Kim, Hongjo; Bang, Seongdeok; Jeong, Hoyoung; Ham, Youngjib; Kim, Hyoungkwan.

In: Automation in Construction, Vol. 92, 01.08.2018, p. 188-198.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Analyzing context and productivity of tunnel earthmoving processes using imaging and simulation

AU - Kim, Hongjo

AU - Bang, Seongdeok

AU - Jeong, Hoyoung

AU - Ham, Youngjib

AU - Kim, Hyoungkwan

PY - 2018/8/1

Y1 - 2018/8/1

N2 - This study presents an integrated method of construction-process simulation and vision-based context reasoning for productivity analysis of an earthmoving process in a tunnel. Convolutional networks are used to detect construction equipment in the tunnel CCTV video and the context of the earthmoving process is inferred by the context reasoning process. The construction equipment detection model exhibited enhanced performance, with a mean average precision of 99.09%, and the error rate of the estimated context information was only 1.6% of the actual earthmoving context measured by a human. The estimated context information was used as an input for the WebCYCLONE simulation to generate a productivity and cost analysis report. Sensitivity analysis regarding construction equipment provided a new equipment allocation plan that could reduce the cost of the current earthmoving process by 12.25%.

AB - This study presents an integrated method of construction-process simulation and vision-based context reasoning for productivity analysis of an earthmoving process in a tunnel. Convolutional networks are used to detect construction equipment in the tunnel CCTV video and the context of the earthmoving process is inferred by the context reasoning process. The construction equipment detection model exhibited enhanced performance, with a mean average precision of 99.09%, and the error rate of the estimated context information was only 1.6% of the actual earthmoving context measured by a human. The estimated context information was used as an input for the WebCYCLONE simulation to generate a productivity and cost analysis report. Sensitivity analysis regarding construction equipment provided a new equipment allocation plan that could reduce the cost of the current earthmoving process by 12.25%.

UR - http://www.scopus.com/inward/record.url?scp=85045433345&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045433345&partnerID=8YFLogxK

U2 - 10.1016/j.autcon.2018.04.002

DO - 10.1016/j.autcon.2018.04.002

M3 - Article

VL - 92

SP - 188

EP - 198

JO - Automation in Construction

JF - Automation in Construction

SN - 0926-5805

ER -