Chapter Automated Extraction of Bridge Gradient from Drawings Using Deep Learning

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...

Descripció completa

Guardat en:
Dades bibliogràfiques
Autors principals: Bayer, Hakan, Faltin, Benedikt, König, Markus
Format: Online
Idioma:anglès
Publicat: Firenze University Press 2024
Matèries:
Accés en línia:ONIX_20240402_9791221502893_33
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
_version_ 1869530336040321024
author Bayer, Hakan
Faltin, Benedikt
König, Markus
author_browse Bayer, Hakan
Faltin, Benedikt
König, Markus
author_facet Bayer, Hakan
Faltin, Benedikt
König, Markus
author_sort Bayer, Hakan
collection Directory of Open Access Books
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
format Online
id doab-20.500.12854ir-137057
institution Directory of Open Access Books
language eng
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher Firenze University Press
publisherStr Firenze University Press
record_format ojs
spelling doab-20.500.12854ir-1370572024-05-11T19:00:55Z 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 2024-05-11T19:00:53Z 2024-05-11T19:00:53Z 2024-04-02T15:45:24Z 2023 chapter ONIX_20240402_9791221502893_33 2704-5846 https://library.oapen.org/handle/20.500.12657/89064 9791221502893 https://directory.doabooks.org/handle/20.500.12854/137057 eng Proceedings e report open access image/jpeg n/a https://library.oapen.org/bitstream/20.500.12657/89064/1/9791221502893_68.pdf Firenze University Press 10.36253/979-12-215-0289-3.68 10.36253/979-12-215-0289-3.68 2ec4474d-93b1-4cfa-b313-9c6019b51b1a 9791221502893 8 Florence open access
spellingShingle 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
Bayer, Hakan
Faltin, Benedikt
König, Markus
Chapter Automated Extraction of Bridge Gradient from Drawings Using Deep Learning
title Chapter Automated Extraction of Bridge Gradient from Drawings Using Deep Learning
title_full Chapter Automated Extraction of Bridge Gradient from Drawings Using Deep Learning
title_fullStr Chapter Automated Extraction of Bridge Gradient from Drawings Using Deep Learning
title_full_unstemmed Chapter Automated Extraction of Bridge Gradient from Drawings Using Deep Learning
title_short Chapter Automated Extraction of Bridge Gradient from Drawings Using Deep Learning
title_sort chapter automated extraction of bridge gradient from drawings using deep learning
topic 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
topic_facet 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
url ONIX_20240402_9791221502893_33
work_keys_str_mv AT bayerhakan chapterautomatedextractionofbridgegradientfromdrawingsusingdeeplearning
AT faltinbenedikt chapterautomatedextractionofbridgegradientfromdrawingsusingdeeplearning
AT konigmarkus chapterautomatedextractionofbridgegradientfromdrawingsusingdeeplearning