Human computer interactive damage inspection for structural management system구조물 관리 시스템을 위한 인간 컴퓨터 상호 작용 기반 손상 검사

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 1
  • Download : 0
Although new technology driven methods have been utilized to overcome the limitation of human based visual inspection, the human based visual inspection is the most widely used nowadays and there are still unresolved issues. Firstly, onsite inspectors have difficulty in finding the previously detected damage location and tracking their status at onsite. For example, an inspector still marks damage location on a target structure with chalks or on drawings, while comparing the current status of existing damages to their previous status as documented onsite. Secondly, current inspection reports are in paper-based documents, making it difficult to accurately determine the damage location and its chronological change. In this study, two approaches are proposed to improve the convenience of the onsite inspectors. First, a method to localize damage in BIM model in real time based on visual-inertial odometry using a few seconds of images and IMU measurements is developed. The developed method automates the full process from damage detection to integrating the damage with a BIM model without manual labor. Secondly, a mixed reality-based structural inspection system with onsite damage information marking is developed. The developed system detects structural damage, creates a holographic marker with damage information on the actual physical damage, and displays the marker onsite via an mixed reality headset. Since inspectors can view the marker with damage information in real-time on the display, they can easily identify where the previous damages have occurred and if the size of the damage is increasing. The performances of the two approaches were verified through a field test at a tunnel and a campus building.
Advisors
손훈researcher
Description
한국과학기술원 :건설및환경공학과,
Publisher
한국과학기술원
Issue Date
2023
Identifier
325007
Language
eng
Description

학위논문(박사) - 한국과학기술원 : 건설및환경공학과, 2023.8,[vi, 90 p. :]

Keywords

인간-컴퓨터 상호작용▼a딥러닝▼a구조물 결함 탐지▼a구조물 결함 관리▼a빌딩 정보 모델링▼a혼합현실; HCI▼aDeep learning▼aStructural damage inspection▼aStructural damage management▼aBIM▼aMixed reality

URI
http://hdl.handle.net/10203/320780
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1046546&flag=dissertation
Appears in Collection
CE-Theses_Ph.D.(박사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0