Computer vision techniques for construction safety and health monitoring

Joonoh Seo, Sanguk Han, Sanghyun Lee, Hyoungkwan Kim

Research output: Contribution to journalArticle

109 Citations (Scopus)

Abstract

For construction safety and health, continuous monitoring of unsafe conditions and action is essential in order to eliminate potential hazards in a timely manner. As a robust and automated means of field observation, computer vision techniques have been applied for the extraction of safety related information from site images and videos, and regarded as effective solutions complementary to current time-consuming and unreliable manual observational practices. Although some research efforts have been directed toward computer vision-based safety and health monitoring, its application in real practice remains premature due to a number of technical issues and research challenges in terms of reliability, accuracy, and applicability. This paper thus reviews previous attempts in construction applications from both technical and practical perspectives in order to understand the current status of computer vision techniques, which in turn suggests the direction of future research in the field of computer vision-based safety and health monitoring. Specifically, this paper categorizes previous studies into three groups - object detection, object tracking, and action recognition - based on types of information required to evaluate unsafe conditions and acts. The results demonstrate that major research challenges include comprehensive scene understanding, varying tracking accuracy by camera position, and action recognition of multiple equipment and workers. In addition, we identified several practical issues including a lack of task-specific and quantifiable metrics to evaluate the extracted information in safety context, technical obstacles due to dynamic conditions at construction sites and privacy issues. These challenges indicate a need for further research in these areas. Accordingly, this paper provides researchers insights into advancing knowledge and techniques for computer vision-based safety and health monitoring, and offers fresh opportunities and considerations to practitioners in understanding and adopting the techniques.

Original languageEnglish
Pages (from-to)239-251
Number of pages13
JournalAdvanced Engineering Informatics
Volume29
Issue number2
DOIs
Publication statusPublished - 2015 Apr 1

Fingerprint

Computer vision
Health
Monitoring
Hazards
Cameras

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Artificial Intelligence

Cite this

Seo, Joonoh ; Han, Sanguk ; Lee, Sanghyun ; Kim, Hyoungkwan. / Computer vision techniques for construction safety and health monitoring. In: Advanced Engineering Informatics. 2015 ; Vol. 29, No. 2. pp. 239-251.
@article{f264b07e6b0b4a3fb12982b89d3b6547,
title = "Computer vision techniques for construction safety and health monitoring",
abstract = "For construction safety and health, continuous monitoring of unsafe conditions and action is essential in order to eliminate potential hazards in a timely manner. As a robust and automated means of field observation, computer vision techniques have been applied for the extraction of safety related information from site images and videos, and regarded as effective solutions complementary to current time-consuming and unreliable manual observational practices. Although some research efforts have been directed toward computer vision-based safety and health monitoring, its application in real practice remains premature due to a number of technical issues and research challenges in terms of reliability, accuracy, and applicability. This paper thus reviews previous attempts in construction applications from both technical and practical perspectives in order to understand the current status of computer vision techniques, which in turn suggests the direction of future research in the field of computer vision-based safety and health monitoring. Specifically, this paper categorizes previous studies into three groups - object detection, object tracking, and action recognition - based on types of information required to evaluate unsafe conditions and acts. The results demonstrate that major research challenges include comprehensive scene understanding, varying tracking accuracy by camera position, and action recognition of multiple equipment and workers. In addition, we identified several practical issues including a lack of task-specific and quantifiable metrics to evaluate the extracted information in safety context, technical obstacles due to dynamic conditions at construction sites and privacy issues. These challenges indicate a need for further research in these areas. Accordingly, this paper provides researchers insights into advancing knowledge and techniques for computer vision-based safety and health monitoring, and offers fresh opportunities and considerations to practitioners in understanding and adopting the techniques.",
author = "Joonoh Seo and Sanguk Han and Sanghyun Lee and Hyoungkwan Kim",
year = "2015",
month = "4",
day = "1",
doi = "10.1016/j.aei.2015.02.001",
language = "English",
volume = "29",
pages = "239--251",
journal = "Advanced Engineering Informatics",
issn = "1474-0346",
publisher = "Elsevier Limited",
number = "2",

}

Computer vision techniques for construction safety and health monitoring. / Seo, Joonoh; Han, Sanguk; Lee, Sanghyun; Kim, Hyoungkwan.

In: Advanced Engineering Informatics, Vol. 29, No. 2, 01.04.2015, p. 239-251.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Computer vision techniques for construction safety and health monitoring

AU - Seo, Joonoh

AU - Han, Sanguk

AU - Lee, Sanghyun

AU - Kim, Hyoungkwan

PY - 2015/4/1

Y1 - 2015/4/1

N2 - For construction safety and health, continuous monitoring of unsafe conditions and action is essential in order to eliminate potential hazards in a timely manner. As a robust and automated means of field observation, computer vision techniques have been applied for the extraction of safety related information from site images and videos, and regarded as effective solutions complementary to current time-consuming and unreliable manual observational practices. Although some research efforts have been directed toward computer vision-based safety and health monitoring, its application in real practice remains premature due to a number of technical issues and research challenges in terms of reliability, accuracy, and applicability. This paper thus reviews previous attempts in construction applications from both technical and practical perspectives in order to understand the current status of computer vision techniques, which in turn suggests the direction of future research in the field of computer vision-based safety and health monitoring. Specifically, this paper categorizes previous studies into three groups - object detection, object tracking, and action recognition - based on types of information required to evaluate unsafe conditions and acts. The results demonstrate that major research challenges include comprehensive scene understanding, varying tracking accuracy by camera position, and action recognition of multiple equipment and workers. In addition, we identified several practical issues including a lack of task-specific and quantifiable metrics to evaluate the extracted information in safety context, technical obstacles due to dynamic conditions at construction sites and privacy issues. These challenges indicate a need for further research in these areas. Accordingly, this paper provides researchers insights into advancing knowledge and techniques for computer vision-based safety and health monitoring, and offers fresh opportunities and considerations to practitioners in understanding and adopting the techniques.

AB - For construction safety and health, continuous monitoring of unsafe conditions and action is essential in order to eliminate potential hazards in a timely manner. As a robust and automated means of field observation, computer vision techniques have been applied for the extraction of safety related information from site images and videos, and regarded as effective solutions complementary to current time-consuming and unreliable manual observational practices. Although some research efforts have been directed toward computer vision-based safety and health monitoring, its application in real practice remains premature due to a number of technical issues and research challenges in terms of reliability, accuracy, and applicability. This paper thus reviews previous attempts in construction applications from both technical and practical perspectives in order to understand the current status of computer vision techniques, which in turn suggests the direction of future research in the field of computer vision-based safety and health monitoring. Specifically, this paper categorizes previous studies into three groups - object detection, object tracking, and action recognition - based on types of information required to evaluate unsafe conditions and acts. The results demonstrate that major research challenges include comprehensive scene understanding, varying tracking accuracy by camera position, and action recognition of multiple equipment and workers. In addition, we identified several practical issues including a lack of task-specific and quantifiable metrics to evaluate the extracted information in safety context, technical obstacles due to dynamic conditions at construction sites and privacy issues. These challenges indicate a need for further research in these areas. Accordingly, this paper provides researchers insights into advancing knowledge and techniques for computer vision-based safety and health monitoring, and offers fresh opportunities and considerations to practitioners in understanding and adopting the techniques.

UR - http://www.scopus.com/inward/record.url?scp=84937513003&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937513003&partnerID=8YFLogxK

U2 - 10.1016/j.aei.2015.02.001

DO - 10.1016/j.aei.2015.02.001

M3 - Article

AN - SCOPUS:84937513003

VL - 29

SP - 239

EP - 251

JO - Advanced Engineering Informatics

JF - Advanced Engineering Informatics

SN - 1474-0346

IS - 2

ER -