콘크리트 교량 상태평가를 위한 딥러닝 기반 손상 탐지 프로토타입 개발

Recently, research has been actively conducted on the technology of inspection facilities through image-based analysis assessment of human-inaccessible facilities. This research was conducted to study the conditions of deep learning-based imaging data on bridges and to develop an evaluation prototyp...

Full description

Saved in:
Bibliographic Details
Published inKSCE Journal of Civil and Environmental Engineering Research Vol. 42; no. 1; pp. 107 - 116
Main Authors 남우석, 정현준, 박경한, 김철민, 김규선, Nam, Woo-Suk, Jung, Hyunjun, Park, Kyung-Han, Kim, Cheol-Min, Kim, Gyu-Seon
Format Journal Article
LanguageKorean
Published 대한토목학회 01.02.2022
Subjects
Online AccessGet full text
ISSN1015-6348
2799-9629
DOI10.12652/Ksce.2022.42.1.0107

Cover

Abstract Recently, research has been actively conducted on the technology of inspection facilities through image-based analysis assessment of human-inaccessible facilities. This research was conducted to study the conditions of deep learning-based imaging data on bridges and to develop an evaluation prototype program for bridges. To develop a deep learning-based bridge damage detection prototype, the Semantic Segmentation model, which enables damage detection and quantification among deep learning models, applied Mask-RCNN and constructed learning data 5,140 (including open-data) and labeling suitable for damage types. As a result of performance modeling verification, precision and reproduction rate analysis of concrete cracks, stripping/slapping, rebar exposure and paint stripping showed that the precision was 95.2 %, and the recall was 93.8 %. A 2nd performance verification was performed on onsite data of crack concrete using damage rate of bridge members. 최근 안전점검자가 접근성 문제로 점검이 어려운 교량 부재의 상태평가를 위해 영상분석 기반의 시설물 점검 기법연구가 활발히 진행 중이다. 본 논문은 교량을 대상으로 딥러닝 기반 영상정보에 대해서 상태평가 연구를 진행하였고 이에 대한 평가 프로그램(프로토타입)을 개발하였다. 딥러닝 기반 교량 손상탐지 프로토타입을 개발하기 위해 딥러닝 모델 중 손상 검출 및 정량화가 가능한 의미론적 분할 모델인 Mask-RCNN를 적용하였고 학습데이터 6,540장(오픈 데이터 포함)과 손상유형에 적합한 레이블링을 구성하였다. 모델링에 대한 성능검증한 결과, 콘크리트 균열, 박리/박락, 철근노출과 도장 박리에 대한 정밀도(precision)는 95.2 %, 재현율(recall)은 93.8 % 나타내었다. 또한, 교량 콘크리트 부재 손상율을 이용하여 콘크리트 균열 실 데이터를 2차 성능검증 하였다.
AbstractList 최근 안전점검자가 접근성 문제로 점검이 어려운 교량 부재의 상태평가를 위해 영상분석 기반의 시설물 점검 기법연구가 활발히 진행 중이다. 본 논문은 교량을 대상으로 딥러닝 기반 영상정보에 대해서 상태평가 연구를 진행하였고 이에 대한 평가 프로그램(프로토타입)을 개발하였다. 딥러닝 기반 교량 손상탐지 프로토타입을 개발하기 위해 딥러닝 모델 중 손상 검출 및 정량화가 가능한 의미론적 분할 모델인 Mask-RCNN를 적용하였고 학습데이터 6,540장(오픈 데이터 포함)과 손상유형에 적합한 레이블링을 구성하였다. 모델링에 대한 성능검증한 결과, 콘크리트 균열, 박리/박락, 철근노출과 도장 박리에 대한 정밀도(precision)는 95.2 %, 재현율(recall)은 93.8 % 나타내었다. 또한, 교량 콘크리트 부재 손상율을 이용하여 콘크리트 균열 실 데이터를 2차 성능검증 하였다. Recently, research has been actively conducted on the technology of inspection facilities through image-based analysis assessment ofhuman-inaccessible facilities. This research was conducted to study the conditions of deep learning-based imaging data on bridges and to develop an evaluation prototype program for bridges. To develop a deep learning-based bridge damage detection prototype, the Semantic Segmentation model, which enables damage detection and quantification among deep learning models, applied Mask-RCNN and constructed learning data 5,140 (including open-data) and labeling suitable for damage types. As a result of performance modeling verification, precision and reproduction rate analysis of concrete cracks, stripping/slapping, rebar exposure and paint stripping showed that the precision was 95.2 %, and the recall was 93.8 %. A 2nd performance verification was performed on onsite data of crack concrete using damage rate of bridge members. KCI Citation Count: 1
Recently, research has been actively conducted on the technology of inspection facilities through image-based analysis assessment of human-inaccessible facilities. This research was conducted to study the conditions of deep learning-based imaging data on bridges and to develop an evaluation prototype program for bridges. To develop a deep learning-based bridge damage detection prototype, the Semantic Segmentation model, which enables damage detection and quantification among deep learning models, applied Mask-RCNN and constructed learning data 5,140 (including open-data) and labeling suitable for damage types. As a result of performance modeling verification, precision and reproduction rate analysis of concrete cracks, stripping/slapping, rebar exposure and paint stripping showed that the precision was 95.2 %, and the recall was 93.8 %. A 2nd performance verification was performed on onsite data of crack concrete using damage rate of bridge members. 최근 안전점검자가 접근성 문제로 점검이 어려운 교량 부재의 상태평가를 위해 영상분석 기반의 시설물 점검 기법연구가 활발히 진행 중이다. 본 논문은 교량을 대상으로 딥러닝 기반 영상정보에 대해서 상태평가 연구를 진행하였고 이에 대한 평가 프로그램(프로토타입)을 개발하였다. 딥러닝 기반 교량 손상탐지 프로토타입을 개발하기 위해 딥러닝 모델 중 손상 검출 및 정량화가 가능한 의미론적 분할 모델인 Mask-RCNN를 적용하였고 학습데이터 6,540장(오픈 데이터 포함)과 손상유형에 적합한 레이블링을 구성하였다. 모델링에 대한 성능검증한 결과, 콘크리트 균열, 박리/박락, 철근노출과 도장 박리에 대한 정밀도(precision)는 95.2 %, 재현율(recall)은 93.8 % 나타내었다. 또한, 교량 콘크리트 부재 손상율을 이용하여 콘크리트 균열 실 데이터를 2차 성능검증 하였다.
Author Park, Kyung-Han
박경한
Kim, Gyu-Seon
김규선
정현준
Jung, Hyunjun
남우석
Nam, Woo-Suk
김철민
Kim, Cheol-Min
Author_xml – sequence: 1
  fullname: 남우석
– sequence: 2
  fullname: 정현준
– sequence: 3
  fullname: 박경한
– sequence: 4
  fullname: 김철민
– sequence: 5
  fullname: 김규선
– sequence: 6
  fullname: Nam, Woo-Suk
– sequence: 7
  fullname: Jung, Hyunjun
– sequence: 8
  fullname: Park, Kyung-Han
– sequence: 9
  fullname: Kim, Cheol-Min
– sequence: 10
  fullname: Kim, Gyu-Seon
BackLink https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002807812$$DAccess content in National Research Foundation of Korea (NRF)
BookMark eNot0D1PwkAAxvGLwUREvoHDLQ4OrffSHr2REF8QEhLDXq_lahoIJNQPAAFJ0EEGTBiq6IAuDF1MGPQLcb3vIIrTf_nlGZ59kGl32hKAQ4xMTJhNTiqRL02CCDEtYmITYVTYAVlS4NzgjPAMyGKEbYNRy9kD-SgKPYQwthyOeRZcp98z3V-q96W-X8H150TNxzAd9PUg1o_jddJTiy-YxkP9FEM1Xaj5Uj08w_UqUckMpqPJhkI9mKQfPainQ_UW69GrHvTSlzu4TmKVxAdgNxCtSOb_mwP1s9N66cKo1s7LpWLVaDKLGyKgFivYHpMN4RDpWwj7jQBJj0gpBAoww0yiBncEJtRzAuL5wvZtKqlNRSEQNAeOt7PtbuA2_dDtiPCvNx232XWLV_WyyzlhDuUbe7S1zTC6Dd12I2q5l8VK7fdD5HBKKUaMUPoDuDiDKw
ContentType Journal Article
DBID JDI
ACYCR
DEWEY 624
DOI 10.12652/Ksce.2022.42.1.0107
DatabaseName [Open Access] KoreaScience
Korean Citation Index
DatabaseTitleList

DeliveryMethod fulltext_linktorsrc
Discipline Engineering
DocumentTitleAlternate Development of Deep Learning-Based Damage Detection Prototype for Concrete Bridge Condition Evaluation
EISSN 2799-9629
EndPage 116
ExternalDocumentID oai_kci_go_kr_ARTI_9926839
JAKO202208933310623
GroupedDBID .UV
ALMA_UNASSIGNED_HOLDINGS
JDI
ACYCR
M~E
ID FETCH-LOGICAL-k649-af34675b6eda82ec401cdf0eb2eeaa0f1616e0d98a123b8f2bca5c53e353a7fa3
ISSN 1015-6348
IngestDate Tue Nov 21 21:41:52 EST 2023
Fri Dec 22 11:58:46 EST 2023
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Issue 1
Language Korean
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-k649-af34675b6eda82ec401cdf0eb2eeaa0f1616e0d98a123b8f2bca5c53e353a7fa3
Notes KISTI1.1003/JNL.JAKO202208933310623
http://kscejournal.or.kr/jksce/XmlViewer/f411908
OpenAccessLink http://click.ndsl.kr/servlet/LinkingDetailView?cn=JAKO202208933310623&dbt=JAKO&org_code=O481&site_code=SS1481&service_code=01
PageCount 10
ParticipantIDs nrf_kci_oai_kci_go_kr_ARTI_9926839
kisti_ndsl_JAKO202208933310623
PublicationCentury 2000
PublicationDate 2022-02
PublicationDateYYYYMMDD 2022-02-01
PublicationDate_xml – month: 02
  year: 2022
  text: 2022-02
PublicationDecade 2020
PublicationTitle KSCE Journal of Civil and Environmental Engineering Research
PublicationTitleAlternate 대한토목학회논문집
PublicationYear 2022
Publisher 대한토목학회
Publisher_xml – name: 대한토목학회
SSID ssib001148919
ssib053377074
ssib023393606
ssib050734827
ssib001148918
ssib023393609
ssib023393608
ssib023393607
ssib036278542
ssib005299834
ssib005299833
ssib001148922
ssib001148920
ssib001148921
ssib005299836
ssib005299835
ssib008451731
Score 1.7963374
Snippet Recently, research has been actively conducted on the technology of inspection facilities through image-based analysis assessment of human-inaccessible...
최근 안전점검자가 접근성 문제로 점검이 어려운 교량 부재의 상태평가를 위해 영상분석 기반의 시설물 점검 기법연구가 활발히 진행 중이다. 본 논문은 교량을 대상으로...
SourceID nrf
kisti
SourceType Open Website
Open Access Repository
StartPage 107
SubjectTerms 토목공학
Title 콘크리트 교량 상태평가를 위한 딥러닝 기반 손상 탐지 프로토타입 개발
URI http://click.ndsl.kr/servlet/LinkingDetailView?cn=JAKO202208933310623&dbt=JAKO&org_code=O481&site_code=SS1481&service_code=01
https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002807812
Volume 42
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
ispartofPNX 대한토목학회논문집(국문), 2022, 42(1), 220, pp.107-116
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources (selected full-text only)
  customDbUrl:
  eissn: 2799-9629
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssib050734827
  issn: 1015-6348
  databaseCode: M~E
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR3LbtNA0CrlAgfEU5RHZSH2FKXYu37sHh3HVWlVOFCk3oLt2CgKSqW2cOgBtUqpVDjQQ5F6CBQOhUsPuSD1AD8Ux__A7K5jm7QSj4vtmZ2d2d3Zx0yyO6so90MaR9SHgWSRJjgolh1UYRFm1TgMTWLbBIciWPXiI2vuqTG_bC5PnNsony5ZD2bCjTPPlfyPVgEHeuWnZP9BszlTQMA36BeeoGF4_pWOkeeiWh0xirw6mITIcZFXQ44lPgDjoBqtIA9eJmIaT2OziLIKz0cJz8GpCGKSnKcJao3vf-CcTFRzBTVQUIMTMeDEUcDK4OmSpxRM4bsu5VHOBFDwZFTKs0QRMsGVkWSBcmwQKFDAlMsB0fqoVFAbLaOmgpp5iJqVrKDMHYlxy3b2whPXq5SMbbf1qiWDInjFyT4eUrkIx5hvQhz1QVEljBwqhAppnmgGVi9IXF46aBRPqIGXHTBQCa3MpSZJgAXm-ho1Y0ECKSyrHZA4svFnUXbtePajDPjzWr7BRa4jYGVB95dBREcLjYFPDSi5amQX_2YGiC4Pn55a27Bl8mC5C2shD--K8YyBZ_QZLc9cDiU-tsTnGy_nnYXHPK8GZioByx6M33PKeQwrIr_2ZPG1V5jS4Cezkt0iYfY7XHI1JKyPwaVQcDAD0JJrIWFjDDbH4MJUpoap28U_1pgQRqxih0AG22MwHYPz8oPdZtPR5c8Ag1tE8oi4HCYwU2kiiHuuy-zkLdfDgzO0AO4t9_laYKV2VuOSlbp0WbmU9XjVkXPFFWWivXJVuVjq5deUZ8OfB-nWcfL1OH17og6-7yWHu-qwu5V2e-n73UF_Mzn6oQ572-mHnprsHyWHx8m7j-rgpJ_0D9Thzh6Qqml3b_htU033t5MvvXTnc9rdHH56ow76vaTfu64szXpL7lw1u2el2rYMVvVjAnO0GVhR06c4Cg1ND5uxFgU4inxfi8EntCKtyagPVm5AYxyEvgkzeURM4tuxT24ok52VTnRTUbHhM50H0bMDZjQNjUFD-2Ggx5oZNG2LTSnTookanebai8YZnXFKuQdt12iHrQaPe8_fz1ca7dUGePcPG4xhCxy6W3_iclu5UAzKO8rk-urL6C74DuvBtOjkvwDk6-Hx
linkProvider ISSN International Centre
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%EC%BD%98%ED%81%AC%EB%A6%AC%ED%8A%B8+%EA%B5%90%EB%9F%89+%EC%83%81%ED%83%9C%ED%8F%89%EA%B0%80%EB%A5%BC+%EC%9C%84%ED%95%9C+%EB%94%A5%EB%9F%AC%EB%8B%9D+%EA%B8%B0%EB%B0%98+%EC%86%90%EC%83%81+%ED%83%90%EC%A7%80+%ED%94%84%EB%A1%9C%ED%86%A0%ED%83%80%EC%9E%85+%EA%B0%9C%EB%B0%9C&rft.jtitle=KSCE+Journal+of+Civil+and+Environmental+Engineering+Research&rft.au=%EB%82%A8%EC%9A%B0%EC%84%9D&rft.au=%EC%A0%95%ED%98%84%EC%A4%80&rft.au=%EB%B0%95%EA%B2%BD%ED%95%9C&rft.au=%EA%B9%80%EC%B2%A0%EB%AF%BC&rft.date=2022-02-01&rft.issn=1015-6348&rft.volume=42&rft.issue=1&rft.spage=107&rft.epage=116&rft_id=info:doi/10.12652%2FKsce.2022.42.1.0107&rft.externalDBID=n%2Fa&rft.externalDocID=JAKO202208933310623
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1015-6348&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1015-6348&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1015-6348&client=summon