UAV Bridge Inspection through Evaluated 3D Reconstructions

Siyuan Chen, Debra Laefer, Eleni Mangina, S. M.Iman Zolanvari, Jonathan Byrne

Research output: Contribution to journalArticle

Abstract

Imagery-based, three-dimensional (3D) reconstruction from unmanned aerial vehicles (UAVs) holds the potential to provide safer, more economical, and less disruptive bridge inspection. In support of those efforts, this paper proposes a process using an imagery-based point cloud. First, a bridge inspection procedure is introduced, including data acquisition, 3D reconstruction, data quality evaluation, and subsequent damage detection. Next, evaluation mechanisms are proposed including checking data coverage, analyzing point distribution, assessing outlier noise, and measuring geometric accuracy. The overall approach is illustrated in the form of a case study with a low-cost UAV. Areas of particular coverage difficulty involved slim features such as railings, in which obtaining sufficient features for image matching proved challenging. Shadowing and large tilt angles hid or weakened texturing surfaces, which also interfered with the matching process.

Original languageEnglish (US)
Article number05019001
JournalJournal of Bridge Engineering
Volume24
Issue number4
DOIs
StatePublished - Apr 1 2019

Fingerprint

Unmanned aerial vehicles (UAV)
Inspection
Railings
Image matching
Texturing
Damage detection
Data acquisition
Costs

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction

Cite this

UAV Bridge Inspection through Evaluated 3D Reconstructions. / Chen, Siyuan; Laefer, Debra; Mangina, Eleni; Zolanvari, S. M.Iman; Byrne, Jonathan.

In: Journal of Bridge Engineering, Vol. 24, No. 4, 05019001, 01.04.2019.

Research output: Contribution to journalArticle

Chen, Siyuan ; Laefer, Debra ; Mangina, Eleni ; Zolanvari, S. M.Iman ; Byrne, Jonathan. / UAV Bridge Inspection through Evaluated 3D Reconstructions. In: Journal of Bridge Engineering. 2019 ; Vol. 24, No. 4.
@article{219da946feab476da5b1e759ef1c8926,
title = "UAV Bridge Inspection through Evaluated 3D Reconstructions",
abstract = "Imagery-based, three-dimensional (3D) reconstruction from unmanned aerial vehicles (UAVs) holds the potential to provide safer, more economical, and less disruptive bridge inspection. In support of those efforts, this paper proposes a process using an imagery-based point cloud. First, a bridge inspection procedure is introduced, including data acquisition, 3D reconstruction, data quality evaluation, and subsequent damage detection. Next, evaluation mechanisms are proposed including checking data coverage, analyzing point distribution, assessing outlier noise, and measuring geometric accuracy. The overall approach is illustrated in the form of a case study with a low-cost UAV. Areas of particular coverage difficulty involved slim features such as railings, in which obtaining sufficient features for image matching proved challenging. Shadowing and large tilt angles hid or weakened texturing surfaces, which also interfered with the matching process.",
author = "Siyuan Chen and Debra Laefer and Eleni Mangina and Zolanvari, {S. M.Iman} and Jonathan Byrne",
year = "2019",
month = "4",
day = "1",
doi = "10.1061/(ASCE)BE.1943-5592.0001343",
language = "English (US)",
volume = "24",
journal = "Journal of Bridge Engineering",
issn = "1084-0702",
publisher = "American Society of Civil Engineers (ASCE)",
number = "4",

}

TY - JOUR

T1 - UAV Bridge Inspection through Evaluated 3D Reconstructions

AU - Chen, Siyuan

AU - Laefer, Debra

AU - Mangina, Eleni

AU - Zolanvari, S. M.Iman

AU - Byrne, Jonathan

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Imagery-based, three-dimensional (3D) reconstruction from unmanned aerial vehicles (UAVs) holds the potential to provide safer, more economical, and less disruptive bridge inspection. In support of those efforts, this paper proposes a process using an imagery-based point cloud. First, a bridge inspection procedure is introduced, including data acquisition, 3D reconstruction, data quality evaluation, and subsequent damage detection. Next, evaluation mechanisms are proposed including checking data coverage, analyzing point distribution, assessing outlier noise, and measuring geometric accuracy. The overall approach is illustrated in the form of a case study with a low-cost UAV. Areas of particular coverage difficulty involved slim features such as railings, in which obtaining sufficient features for image matching proved challenging. Shadowing and large tilt angles hid or weakened texturing surfaces, which also interfered with the matching process.

AB - Imagery-based, three-dimensional (3D) reconstruction from unmanned aerial vehicles (UAVs) holds the potential to provide safer, more economical, and less disruptive bridge inspection. In support of those efforts, this paper proposes a process using an imagery-based point cloud. First, a bridge inspection procedure is introduced, including data acquisition, 3D reconstruction, data quality evaluation, and subsequent damage detection. Next, evaluation mechanisms are proposed including checking data coverage, analyzing point distribution, assessing outlier noise, and measuring geometric accuracy. The overall approach is illustrated in the form of a case study with a low-cost UAV. Areas of particular coverage difficulty involved slim features such as railings, in which obtaining sufficient features for image matching proved challenging. Shadowing and large tilt angles hid or weakened texturing surfaces, which also interfered with the matching process.

UR - http://www.scopus.com/inward/record.url?scp=85060135062&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060135062&partnerID=8YFLogxK

U2 - 10.1061/(ASCE)BE.1943-5592.0001343

DO - 10.1061/(ASCE)BE.1943-5592.0001343

M3 - Article

AN - SCOPUS:85060135062

VL - 24

JO - Journal of Bridge Engineering

JF - Journal of Bridge Engineering

SN - 1084-0702

IS - 4

M1 - 05019001

ER -