Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring

B F Spencer, Vedhus Hoskere, Yasutaka Narazaki

Research output: Contribution to journalReview article

Abstract

Computer vision techniques, in conjunction with acquisition through remote cameras and unmanned aerial vehicles (UAVs), offer promising non-contact solutions to civil infrastructure condition assessment. The ultimate goal of such a system is to automatically and robustly convert the image or video data into actionable information. This paper provides an overview of recent advances in computer vision techniques as they apply to the problem of civil infrastructure condition assessment. In particular, relevant research in the fields of computer vision, machine learning, and structural engineering is presented. The work reviewed is classified into two types: inspection applications and monitoring applications. The inspection applications reviewed include identifying context such as structural components, characterizing local and global visible damage, and detecting changes from a reference image. The monitoring applications discussed include static measurement of strain and displacement, as well as dynamic measurement of displacement for modal analysis. Subsequently, some of the key challenges that persist toward the goal of automated vision-based civil infrastructure and monitoring are presented. The paper concludes with ongoing work aimed at addressing some of these stated challenges.

Original languageEnglish (US)
Pages (from-to)199-222
Number of pages24
JournalEngineering
Volume5
Issue number2
DOIs
StatePublished - Apr 2019

Fingerprint

Computer vision
Inspection
Monitoring
Modal analysis
Unmanned aerial vehicles (UAV)
Structural design
Learning systems
Cameras

Keywords

  • Artificial intelligence
  • Computer vision
  • Machine learning
  • Optical flow
  • Structural inspection and monitoring

ASJC Scopus subject areas

  • Computer Science(all)
  • Environmental Engineering
  • Chemical Engineering(all)
  • Materials Science (miscellaneous)
  • Energy Engineering and Power Technology
  • Engineering(all)

Cite this

Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring. / Spencer, B F; Hoskere, Vedhus; Narazaki, Yasutaka.

In: Engineering, Vol. 5, No. 2, 04.2019, p. 199-222.

Research output: Contribution to journalReview article

Spencer, B F ; Hoskere, Vedhus ; Narazaki, Yasutaka. / Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring. In: Engineering. 2019 ; Vol. 5, No. 2. pp. 199-222.
@article{401fb7756bff4888a14e603e865fbb3b,
title = "Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring",
abstract = "Computer vision techniques, in conjunction with acquisition through remote cameras and unmanned aerial vehicles (UAVs), offer promising non-contact solutions to civil infrastructure condition assessment. The ultimate goal of such a system is to automatically and robustly convert the image or video data into actionable information. This paper provides an overview of recent advances in computer vision techniques as they apply to the problem of civil infrastructure condition assessment. In particular, relevant research in the fields of computer vision, machine learning, and structural engineering is presented. The work reviewed is classified into two types: inspection applications and monitoring applications. The inspection applications reviewed include identifying context such as structural components, characterizing local and global visible damage, and detecting changes from a reference image. The monitoring applications discussed include static measurement of strain and displacement, as well as dynamic measurement of displacement for modal analysis. Subsequently, some of the key challenges that persist toward the goal of automated vision-based civil infrastructure and monitoring are presented. The paper concludes with ongoing work aimed at addressing some of these stated challenges.",
keywords = "Artificial intelligence, Computer vision, Machine learning, Optical flow, Structural inspection and monitoring",
author = "Spencer, {B F} and Vedhus Hoskere and Yasutaka Narazaki",
year = "2019",
month = "4",
doi = "10.1016/j.eng.2018.11.030",
language = "English (US)",
volume = "5",
pages = "199--222",
journal = "Engineering",
issn = "2095-8099",
publisher = "Elsevier Limited",
number = "2",

}

TY - JOUR

T1 - Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring

AU - Spencer, B F

AU - Hoskere, Vedhus

AU - Narazaki, Yasutaka

PY - 2019/4

Y1 - 2019/4

N2 - Computer vision techniques, in conjunction with acquisition through remote cameras and unmanned aerial vehicles (UAVs), offer promising non-contact solutions to civil infrastructure condition assessment. The ultimate goal of such a system is to automatically and robustly convert the image or video data into actionable information. This paper provides an overview of recent advances in computer vision techniques as they apply to the problem of civil infrastructure condition assessment. In particular, relevant research in the fields of computer vision, machine learning, and structural engineering is presented. The work reviewed is classified into two types: inspection applications and monitoring applications. The inspection applications reviewed include identifying context such as structural components, characterizing local and global visible damage, and detecting changes from a reference image. The monitoring applications discussed include static measurement of strain and displacement, as well as dynamic measurement of displacement for modal analysis. Subsequently, some of the key challenges that persist toward the goal of automated vision-based civil infrastructure and monitoring are presented. The paper concludes with ongoing work aimed at addressing some of these stated challenges.

AB - Computer vision techniques, in conjunction with acquisition through remote cameras and unmanned aerial vehicles (UAVs), offer promising non-contact solutions to civil infrastructure condition assessment. The ultimate goal of such a system is to automatically and robustly convert the image or video data into actionable information. This paper provides an overview of recent advances in computer vision techniques as they apply to the problem of civil infrastructure condition assessment. In particular, relevant research in the fields of computer vision, machine learning, and structural engineering is presented. The work reviewed is classified into two types: inspection applications and monitoring applications. The inspection applications reviewed include identifying context such as structural components, characterizing local and global visible damage, and detecting changes from a reference image. The monitoring applications discussed include static measurement of strain and displacement, as well as dynamic measurement of displacement for modal analysis. Subsequently, some of the key challenges that persist toward the goal of automated vision-based civil infrastructure and monitoring are presented. The paper concludes with ongoing work aimed at addressing some of these stated challenges.

KW - Artificial intelligence

KW - Computer vision

KW - Machine learning

KW - Optical flow

KW - Structural inspection and monitoring

UR - http://www.scopus.com/inward/record.url?scp=85063608159&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063608159&partnerID=8YFLogxK

U2 - 10.1016/j.eng.2018.11.030

DO - 10.1016/j.eng.2018.11.030

M3 - Review article

AN - SCOPUS:85063608159

VL - 5

SP - 199

EP - 222

JO - Engineering

JF - Engineering

SN - 2095-8099

IS - 2

ER -