9791221502893_68.pdf

Digital methods such as Building Information Modeling (BIM) can be leveraged, to improve the efficiency of maintenance planning of bridges. However, this requires digital building models, which are rarely available. Consequently, these models must be created retrospectively, which is time-consuming...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Γλώσσα:English
Έκδοση: Firenze University Press 2024
Διαθέσιμο Online:https://books.fupress.com/doi/capitoli/979-12-215-0289-3_68
id oapen-20.500.12657-89064
record_format dspace
spelling oapen-20.500.12657-890642024-04-03T02:23:04Z Chapter Automated Extraction of Bridge Gradient from Drawings Using Deep Learning Bayer, Hakan Faltin, Benedikt König, Markus Building Information Modeling Computer Vision Deep Learning Symbol Detection Optical Character Recognition Construction Drawings thema EDItEUR::U Computing and Information Technology::UT Computer networking and communications::UTV Virtualization Digital methods such as Building Information Modeling (BIM) can be leveraged, to improve the efficiency of maintenance planning of bridges. However, this requires digital building models, which are rarely available. Consequently, these models must be created retrospectively, which is time-consuming when done manually. Naturally, there is a great interest in the industry to automate the process of retro-digitization. This paper contributes to these efforts by proposing a multistage pipeline to automatically extract the gradient of a bridge from pixel-based construction drawings using deep learning. The bridge gradient, a key element of the structure’s axis, is critical for describing the elevation profile and axis slope. This information is implicitly contained in the longitudinal view of bridge drawings as gradient symbols. To extract this information, the well-established object detection model YOLOv5 is employed to locate the gradient symbols inside the drawings. Subsequently, EasyOCR and heuristic rules are applied to extract the relevant gradient parameters associated with each detected symbol. The extracted parameters are then exported in a machine-interpretable format to facilitate seamless integration into other applications. The results show a promising 98% accuracy in symbol detection and an overall accuracy of 70%. Consequently, the pipeline represents a significant advance in automating the retro-digitization process for existing bridges by reducing the time and effort required 2024-04-02T15:45:24Z 2024-04-02T15:45:24Z 2023 chapter ONIX_20240402_9791221502893_33 2704-5846 9791221502893 https://library.oapen.org/handle/20.500.12657/89064 eng Proceedings e report application/pdf n/a 9791221502893_68.pdf https://books.fupress.com/doi/capitoli/979-12-215-0289-3_68 Firenze University Press 10.36253/979-12-215-0289-3.68 10.36253/979-12-215-0289-3.68 bf65d21a-78e5-4ba2-983a-dbfa90962870 9791221502893 137 8 Florence open access
institution OAPEN
collection DSpace
language English
description Digital methods such as Building Information Modeling (BIM) can be leveraged, to improve the efficiency of maintenance planning of bridges. However, this requires digital building models, which are rarely available. Consequently, these models must be created retrospectively, which is time-consuming when done manually. Naturally, there is a great interest in the industry to automate the process of retro-digitization. This paper contributes to these efforts by proposing a multistage pipeline to automatically extract the gradient of a bridge from pixel-based construction drawings using deep learning. The bridge gradient, a key element of the structure’s axis, is critical for describing the elevation profile and axis slope. This information is implicitly contained in the longitudinal view of bridge drawings as gradient symbols. To extract this information, the well-established object detection model YOLOv5 is employed to locate the gradient symbols inside the drawings. Subsequently, EasyOCR and heuristic rules are applied to extract the relevant gradient parameters associated with each detected symbol. The extracted parameters are then exported in a machine-interpretable format to facilitate seamless integration into other applications. The results show a promising 98% accuracy in symbol detection and an overall accuracy of 70%. Consequently, the pipeline represents a significant advance in automating the retro-digitization process for existing bridges by reducing the time and effort required
title 9791221502893_68.pdf
spellingShingle 9791221502893_68.pdf
title_short 9791221502893_68.pdf
title_full 9791221502893_68.pdf
title_fullStr 9791221502893_68.pdf
title_full_unstemmed 9791221502893_68.pdf
title_sort 9791221502893_68.pdf
publisher Firenze University Press
publishDate 2024
url https://books.fupress.com/doi/capitoli/979-12-215-0289-3_68
_version_ 1799945282429911040