Detecting Construction Equipment Using a Region-Based Fully Convolutional Network and Transfer Learning

Hongjo Kim, Hyoungkwan Kim, Yong Won Hong, Hyeran Byun

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

For proper construction site management and plan revisions during construction, it is necessary to understand a construction site's status in real time. Many vision-based construction site-monitoring methods exist, but current technology has not achieved the accuracy required to robustly recognize objects such as construction equipment, workers, and materials in actual jobsite images. To address this issue, this paper proposes a deep convolutional network-based construction object-detection method to accurately recognize construction equipment. A deep convolutional network can achieve high performance in various visual tasks, but is not easy to be applied in the construction industry where there is not enough publicly available data for training. This problem is solved by transfer learning, which trains a model for the construction industry by transferring the knowledge of models trained in other domains with a large amount of training data. To evaluate the proposed method, a benchmark data set is created for five classes: a dump truck, excavator, loader, concrete mixer truck, and road roller. This benchmark data set includes various shapes and poses for each class to evaluate the generalization performance of the proposed construction equipment detection model. Experimental results show that the proposed method performs remarkably well, achieving 96.33% mean average precision. In the future, the proposed model can be used to infer the context of construction operations for producing managerial information such as progress, productivity, and safety.

Original languageEnglish
Article number04017082
JournalJournal of Computing in Civil Engineering
Volume32
Issue number2
DOIs
Publication statusPublished - 2018 Mar 1

Fingerprint

Construction equipment
Construction industry
Trucks
Concrete mixers
Excavators
Loaders
Productivity
Monitoring

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Computer Science Applications

Cite this

@article{692f4e441c7747a9be1f95a746cdec88,
title = "Detecting Construction Equipment Using a Region-Based Fully Convolutional Network and Transfer Learning",
abstract = "For proper construction site management and plan revisions during construction, it is necessary to understand a construction site's status in real time. Many vision-based construction site-monitoring methods exist, but current technology has not achieved the accuracy required to robustly recognize objects such as construction equipment, workers, and materials in actual jobsite images. To address this issue, this paper proposes a deep convolutional network-based construction object-detection method to accurately recognize construction equipment. A deep convolutional network can achieve high performance in various visual tasks, but is not easy to be applied in the construction industry where there is not enough publicly available data for training. This problem is solved by transfer learning, which trains a model for the construction industry by transferring the knowledge of models trained in other domains with a large amount of training data. To evaluate the proposed method, a benchmark data set is created for five classes: a dump truck, excavator, loader, concrete mixer truck, and road roller. This benchmark data set includes various shapes and poses for each class to evaluate the generalization performance of the proposed construction equipment detection model. Experimental results show that the proposed method performs remarkably well, achieving 96.33{\%} mean average precision. In the future, the proposed model can be used to infer the context of construction operations for producing managerial information such as progress, productivity, and safety.",
author = "Hongjo Kim and Hyoungkwan Kim and Hong, {Yong Won} and Hyeran Byun",
year = "2018",
month = "3",
day = "1",
doi = "10.1061/(ASCE)CP.1943-5487.0000731",
language = "English",
volume = "32",
journal = "Journal of Computing in Civil Engineering",
issn = "0887-3801",
publisher = "American Society of Civil Engineers (ASCE)",
number = "2",

}

Detecting Construction Equipment Using a Region-Based Fully Convolutional Network and Transfer Learning. / Kim, Hongjo; Kim, Hyoungkwan; Hong, Yong Won; Byun, Hyeran.

In: Journal of Computing in Civil Engineering, Vol. 32, No. 2, 04017082, 01.03.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Detecting Construction Equipment Using a Region-Based Fully Convolutional Network and Transfer Learning

AU - Kim, Hongjo

AU - Kim, Hyoungkwan

AU - Hong, Yong Won

AU - Byun, Hyeran

PY - 2018/3/1

Y1 - 2018/3/1

N2 - For proper construction site management and plan revisions during construction, it is necessary to understand a construction site's status in real time. Many vision-based construction site-monitoring methods exist, but current technology has not achieved the accuracy required to robustly recognize objects such as construction equipment, workers, and materials in actual jobsite images. To address this issue, this paper proposes a deep convolutional network-based construction object-detection method to accurately recognize construction equipment. A deep convolutional network can achieve high performance in various visual tasks, but is not easy to be applied in the construction industry where there is not enough publicly available data for training. This problem is solved by transfer learning, which trains a model for the construction industry by transferring the knowledge of models trained in other domains with a large amount of training data. To evaluate the proposed method, a benchmark data set is created for five classes: a dump truck, excavator, loader, concrete mixer truck, and road roller. This benchmark data set includes various shapes and poses for each class to evaluate the generalization performance of the proposed construction equipment detection model. Experimental results show that the proposed method performs remarkably well, achieving 96.33% mean average precision. In the future, the proposed model can be used to infer the context of construction operations for producing managerial information such as progress, productivity, and safety.

AB - For proper construction site management and plan revisions during construction, it is necessary to understand a construction site's status in real time. Many vision-based construction site-monitoring methods exist, but current technology has not achieved the accuracy required to robustly recognize objects such as construction equipment, workers, and materials in actual jobsite images. To address this issue, this paper proposes a deep convolutional network-based construction object-detection method to accurately recognize construction equipment. A deep convolutional network can achieve high performance in various visual tasks, but is not easy to be applied in the construction industry where there is not enough publicly available data for training. This problem is solved by transfer learning, which trains a model for the construction industry by transferring the knowledge of models trained in other domains with a large amount of training data. To evaluate the proposed method, a benchmark data set is created for five classes: a dump truck, excavator, loader, concrete mixer truck, and road roller. This benchmark data set includes various shapes and poses for each class to evaluate the generalization performance of the proposed construction equipment detection model. Experimental results show that the proposed method performs remarkably well, achieving 96.33% mean average precision. In the future, the proposed model can be used to infer the context of construction operations for producing managerial information such as progress, productivity, and safety.

UR - http://www.scopus.com/inward/record.url?scp=85038391138&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85038391138&partnerID=8YFLogxK

U2 - 10.1061/(ASCE)CP.1943-5487.0000731

DO - 10.1061/(ASCE)CP.1943-5487.0000731

M3 - Article

AN - SCOPUS:85038391138

VL - 32

JO - Journal of Computing in Civil Engineering

JF - Journal of Computing in Civil Engineering

SN - 0887-3801

IS - 2

M1 - 04017082

ER -