ASESMENT OF STATE-OF-THE-ART METHODS FOR BRIDGE INSPECTION: CASE STUDY
- Authors
- Wojcik, B.; Zarski, M.
- Issue Date
- 2020
- Publisher
- POLISH ACAD SCIENCES
- Keywords
- building information modelling; 3D reconstruction; photogammetry; artificial intelligence; bridge inspection
- Citation
- ARCHIVES OF CIVIL ENGINEERING, v.66, no.4, pp 343 - 362
- Pages
- 20
- Journal Title
- ARCHIVES OF CIVIL ENGINEERING
- Volume
- 66
- Number
- 4
- Start Page
- 343
- End Page
- 362
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/63567
- DOI
- 10.24425/ace.2020.135225
- ISSN
- 1230-2945
2300-3103
- Abstract
- Despite the progress in digitization of civil engineering, the process of bridge inspection is still outdated. In most cases, its documentation consists of notes, sketches and photos. This results in significant data loss during structure maintenance and can even lead to critical failures. As a solution to this problem, many researchers see the use of modern technologies that are gaining popularity in civil engineering. Namely Building Information Modelling (BIM), 3D reconstruction and Artificial Intelligence (AI). However, despite their work, no particular solution was implemented. In this article, we evaluated the applicability of state-of-the-art methods based on a case study. We have considered each step starting from data acquisition and ending on BIM model enrichment. Additionally, the comparison of deep learning crack semantic segmentation algorithm with human inspector was performed. Authors believe that this kind of work is crucial for further advancements in the field of bridge maintenance.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of ICT Engineering > School of Electrical and Electronics Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/63567)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.