Intelligent crack identification method for high‐rise buildings aided by synthetic environments

Summary Cracks can develop in high‐rise buildings because of long‐term environmental changes and extreme loading events such as strong winds or earthquakes. Although deep learning‐based identification methods can efficiently identify cracks, the accuracy of crack identification in high‐rise building...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The structural design of tall and special buildings Ročník 33; číslo 12
Hlavní autoři: Yao, Ziluo, Jiang, Sheng, Wang, Shuo, Wang, Jingjing, Liu, Hai, Narazaki, Yasutaka, Cui, Jie, Spencer, Billie F.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Oxford Wiley Subscription Services, Inc 25.08.2024
Témata:
Buildings
Computer graphics
computer vision
crack identification
Cracks
Damage detection
Datasets
Deep learning
DeepLabv3
Earthquakes
Environmental changes
High rise buildings
high‐rise building
Identification
Identification methods
Labels
Neural networks
Seismic activity
Synthetic data
Synthetic environments
UAV
ISSN:1541-7794, 1541-7808
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Summary Cracks can develop in high‐rise buildings because of long‐term environmental changes and extreme loading events such as strong winds or earthquakes. Although deep learning‐based identification methods can efficiently identify cracks, the accuracy of crack identification in high‐rise buildings needs to be improved due to the lack of crack datasets specifically related to high‐rise structures. Moreover, the number of available images of cracks in high‐rise is limited. To this end, this paper establishes an intelligent crack identification method based on a photorealistic synthetic modeling technique. First, a computer graphics (CG) model of a high‐rise building with assumed damage is constructed. Subsequently, the CG model is utilized to generate a dataset that includes photorealistic images of the high‐rise building as well as corresponding labels for various components and types of damage. The generated dataset is then used to train a DeepLabv3 + neural network for structural component and damage identification, followed by validation by employing images of both synthetic and full‐scale high‐rise buildings. The trained network can accurately identify different components in images of the full‐scale, high‐rise building and identify cracks that are intentionally synthesized in those images. The results show that the synthetic dataset generated by the CG model not only allows for fast and efficient labeling for the purpose of neural network training but also outperforms methods that do not consider any application‐specific context in crack identification.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1541-7794
1541-7808
DOI:10.1002/tal.2117