Preliminary Study for Vision A.I-based Automated Quality Supervision Technique of Exterior Insulation and Finishing System - Focusing on Form Bonding Method -

인공지능 영상인식 기반 외단열 공법 품질감리 자동화 기술 기초연구 - 단열재 습식 부착방법을 중심으로 -

  • 윤세빈 (서울과학기술대학교 U-건설관리공학연구소) ;
  • 이병민 (서울과학기술대학교 건축학부(건축공학)) ;
  • 이창수 (고려대학교 건축사회환경공학부) ;
  • 김태훈 (서울과학기술대학교 건축학부(건축공학))
  • Published : 2022.04.20

Abstract

This study proposed vision artificial intelligence-based automated supervision technology for external insulation and finishing system, and basic research was conducted for it. The automated supervision technology proposed in this study consists of the object detection model (YOLOv5) and the part that derives necessary information based on the object detection result and then determines whether the external insulation-related adhesion regulations are complied with. As a result of a test, the judgement accuracy of the proposed model showed about 70%. The results of this study are expected to contribute to securing the external insulation quality and further contributing to the realization of energy-saving eco-friendly buildings. As further research, it is necessary to develop a technology that can improve the accuracy of the object detection model by supplementing the number of data for model training and determine additional related regulations such as the adhesive area ratio.

Keywords

Acknowledgement

본 논문은 2022년 교육부의 재원으로 한국연구재단의 지원(2020R1I1A1A01073510)을 받아 수행된 연구임을 밝히며 이에 감사를 드립니다.