[논문]컴퓨터 비전 기술을 이용한 건설 작업자 보호구 검출 정확도 분석

강성원; 이기석; 유위성; 신윤석; 이명도

doi:10.5345/jkibc.2023.23.1.081

컴퓨터 비전 기술을 이용한 건설 작업자 보호구 검출 정확도 분석
Accuracy Analysis of Construction Worker's Protective Equipment Detection Using Computer Vision Technology 원문보기

한국건축시공학회지 = Journal of the Korea Institute of Building Construction, v.23 no.1, 2023년, pp.81 - 92

강성원 (Department of Architectural Engineering, Kyonggi University) , 이기석 (Department of Architectural Engineering, Kyonggi University) , 유위성 (Department of Economic and Financial Research, Construction & Economy Research Institute of Korea) , 신윤석 (Department of Architectural Engineering, Kyonggi University) , 이명도 (R&D Center, Yunwoo Technologies Co., Ltd.)

Abstract ▼ AI-Helper

According to the 2020 industrial accident reports of the Ministry of Employment and Labor, the number of fatal accidents in the construction industry over the past 5 years has been higher than in other industries. Of these more than 50% of fatal accidents are initially caused by fall accidents. The central government is intensively managing falling/jamming protection device and the use of personal protective equipment to eradicate the inappropriate factors disrupting safety at construction sites. In addition, although efforts have been made to prevent safety accidents with the proposal of the Special Act on Construction Safety, fatalities on construction sites are constantly occurring. Therefore, this study developed a model that automatically detects the wearing state of the worker's safety helmet and belt using computer vision technology. In considerations of conditions occurring at construction sites, we suggest an optimization method, which has been verified in terms of the accuracy and operation speed of the proposed model. As a result, it is possible to improve the efficiency of inspection and patrol by construction site managers, which is expected to contribute to reinforcing competency of safety management.

주제어

표/그림 (12)

그림 Figure 1. An example of object detection
표 Table 1. Review of previous research
그림 Figure 2. Images collected at domestic construction sites
표 Table 2. Image collection overview (Unit : Places, Images)
그림 Figure 3. Image data labeling
그림 Figure 4. Worker detection through YOLO-v3
그림 Figure 5. Class classification through YOLO-v3
표 Table 3. Criteria for detection accuracy evaluation
표 Table 4. Detection accuracy according to distance (Unit : %, number of times)
표 Table 5. Detection accuracy according to the illuminance (Unit : %, number of times)
표 Table 6. Analysis of detection accuracy T-test according to distance (Unit : %), ** P < 0.05
표 Table 7. Analysis of detection accuracy T-test according to illuminance (Unit : %), ** P < 0.05

참고문헌 (24)

Ministry of Employment and Labor. Status of industrial accidents in 2021 [Internet]. Sejong (Korea): Ministry of Employment？and Labor; 2022 Mar 16. Available From: https://www.moel.go.kr/skin/doc.html?fn20220316181319d8e53bb1623f43478809a5e10076b441.hwp&rs/viewer/BBS/2022/
Ministry of Employment and Labor. Statistics on the deaths of industrial accidents in 2020 [Internet]. Sejong (Korea): Ministry？of Employment and Labor; 2021 Dec 30. Available From: https://www.moel.go.kr/skin/doc.html?fn2022090115531410acc82f7e9946809d3b368b4b88a393.hwpx&rs/viewer/BBS/2022/
Korea Occupational Safety Health Agency (KOSHA). Safety and Health Plus in May [Internet]. Ulsan (Korea): Korea？Occupational Safety Health Agency (KOSHA); 2021 Apr 27. Available From: https://www.kosha.or.kr/ebook/fcatalog/ecatalog5.jsp?Dir493&catimage&listCallY&eclangko
Korea Law Information Center. Enforcement Rule Of The Construction Technology Promotion Act. Sejong (Korea): Korea？Law Information Center; 2022 Dec 30. Available From: https://www.law.go.kr/LSW/lsSc.do?section&menuId1&sub？MenuId15&tabMenuId81&eventGubun060101&query%EA%B1%B4%EC%84%A4%EA%B8%B0%EC%88%A0%EC%A7%84%ED%9D%A5%EB%B2%95+%EC%8B%9C%ED%96%89%EA%B7%9C%EC%B9%99#undefined
Ministry of Land, Infrastructure and Transport. Guidelines for Smart Construction Technology Field Application [Internet].？Sejong (Korea): Ministry of Land, Infrastructure and Transport; 2021 Mar 4. Available From: http://m.molit.go.kr/viewer/skin/doc.html?fn57efd7f626b212c57f4959468f9208ef&rs/viewer/result/20210304
Ministry of Land, Infrastructure and Transport. Improving the Safety of Construction Sites by Introducing Smart Safety？Equipment [Internet]. Sejong (Korea): Ministry of Land, Infrastructure and Transport; 2020 Mar 23. Available From:？http://m.molit.go.kr/viewer/skin/doc.html?fnba4f21a0718d1688945470e7c83f2168&rs/viewer/result/20200320
Ministry of Land, Infrastructure and Transport. Smart Construction Technology Roadmap [Internet]. Sejong (Korea): Ministry？of Land, Infrastructure and Transport; 2018 Oct 31. Available From: http://m.molit.go.kr/viewer/skin/doc.html?fn48b98c06c65155bf1c8c1a5289011bf2&rs/viewer/result/20181031
Lee KP, Choi SY, Son TH, Choi SI. Survey on smart technology applications of korean construction companies and strategies？for activation. Seoul (Korea): Construction & Economy Research Institute of Korea Research; 2019 Dec 26. Available From:？http://www.cerik.re.kr/report/research/detail/2330
Lee CH, Kim IS, Lee CY, Shin JM, Kang CH. Application of smart construction technology for quality and productivity？improvement. Magazine of the Korea Concrete Institue. 2021 Nov;33(6):67-72.
Kim WB. Apreliminary study on computer vision based safety helmet detection in constrction [master's thrsis]. [Busan (Korea)]:？Pukyong National University; 2018. 52 p.
Kim MH. Application of deep learning technique for detecting constructio worker wearing safety helmet based on computer？vision [master's thrsis]. [Busan (Korea)]: Pukyong National University; 2019. 69 p.
Shin JK. Real-time monitoring system for personal protective equipment of construction worker using smart technology [Ph.D.？dissertation]. [Suwon (Korea)]: Kyonggi University. 2022. 188 p.
Lee DH. A study on object detection and sensor fusion based on deep learning using lidar and camer [master's thrsis]. [Seoul？(Korea)]: Kookmin University; 2020. 83 p.
Lee YH, Kin YS. Comparison of cnn and yolo for object detection. Journal of the Semiconductor & Display Technology. 2020？Mar;19(1):85-90.
Park YS, Lee SY, Lee KT, Improving personal protective equipment detectionin smart construction. The Journal of the KICS.？2020 Nov;45(12):2202-9. https://doi.org/10.7840/kics.2020.45.12.2202

상세보기
Jeon SY, Park JH, Youn SB, Kim YS, Lee YS, Jeon JH. Real-time worker safety management system using deep learning-based？video analysis algorithm. Smart Media Journal. 2020 Sep;9(3):25-30. https://dx.doi.org/10.30693/SMJ.2020.9.3.25

원문보기 상세보기
Nipun DN, Behzaden AH, Paal SG. Deep learning for site safety: Real-time detection of personal protective equipment.？Automation in Construction. 2020 Apr;112:103085. https://doi.org/10.1016/j.autcon.2020.103085

상세보기
Jeong IS, Kim JW, Chi SH, Roh MG, Biggs H. Solitary work detection of heavy equipment using computer vision. KSCE？Journal of Civil and Environmental Engineering Research. 2021 Aug;41(4):441-7. https://doi.org/10.12652/Ksce.2021.41.4.0441

원문보기 상세보기
Jo BW, Lee YS, Kim DK, Kim JH, Choi PH. Image-based proximity warning system for excavator of construction sites. The？Journal of the Korea Contents Association. 2016 Aug;16(10):588-97. https://doi.org/10.5392/JKCA.2016.16.10.588

원문보기 상세보기
Cho YW, Kang KS, Son BS, Ryu HG. Extraction of workers and heavy equipment and muliti-object tracking using surveillance？system in construction sites. Journal of The Korea Institute of Building Construction. 2021 Oct;21(5):397-408. https://doi.org/10.5345/JKIBC.2021.21.5.397

원문보기 상세보기
Lim TK, Choi BY, Lee DE. Methodology for near-miss identification between earthwork equipment and workers using image？analysis. Korean Journal of Construction Engineering and Management. 2019 Jul;20(4):69-76. https://doi.org/10.6106/KJCEM.2019.20.4.069

원문보기 상세보기
Jeon CW. Deep-learning based detection for small to medium sized tools in indoor construction site [master's thrsis]. [Incheon？(Korea)]: Inha University. 2021. 70 p.
Shin DH, A study on Railway Safety Enhancement on the Utilizing Open Source Computer Vision [Ph.D. dissertation].？[Chungju (Korea)]: Korea National University of Transportation. 2019. 134 p.
Park GJ, Binayark B. Railway facility real-time intruder monitoring system using computer vision and deep learning. Journal of？the Korean Society for Railway. 2020 Jan;23(1):35-44.

상세보기

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증