• Technical Name
  • 以深度學習與數位孿生輔助工地鋼筋查驗
  • Operator
  • National Taiwan University
  • Booth
  • AIoT&智慧應用 AIoT & Smart Applications
  • Contact
  • 陳翊翔
  • Email
  • diamond@caece.net
Technical Description This technique combines deep learningdigital twin technologies to connect the designconstruction processto achieve construction-site rebar inspection, issue tracking, verificationmaintenance. This core component of this method is based on the image collection of rebar frames, digital twin creation, cooperative machine learning,the rebar inspection module development. The BIM model was automatically matchedcompared with the 4D digital twin with features of point cloudtime sequence.
Scientific Breakthrough We proposed a novel construction-site rebar inspection technique powered by deep learningdigital twin. Our breakthrough contains four major parts. First, a dataset of on-site rebar assembly images with high quality labelingspatial information . Second is the rebar feature recognition model based on a deep learning algorithm. The third is the combination of deep learningdigital twin to realize the point cloud feature recognition of rebars. The fourth is the design-based on-site rebar inspection method, which automatically compares BIMthe point cloud segmentation.
Industrial Applicability Deep learning4D digital twin technology drive the digital transformation in the construction engineering industry. This system can assist site supervision units in completing inspections more safelyquicklyuses time-series data to track issues. This system enables smart inspection of rebars, real-time reviewmaintenance of construction sites, engineering issue trackingdesign reviews,visualization of inspection results. The potential commercial value of this project lies in the integration of designconstruction through deep learningdigital twin technology.
本網站使用您的Cookie於優化網站。繼續瀏覽網站即表示您同意本公司隱私權政策,您可至隱私權政策了解詳細資訊。