A study on methods and classification conditions for building facade materials
Artificial Intelligence (AI) has been a popular topic in this age of technology. In the construction industry, it plays an vital role in improving the productivity and efficiency of work. This paper focuses on the development of an automated crack detection system using AI technology. The purpose is...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/145391 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-145391 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1453912020-12-21T02:54:34Z A study on methods and classification conditions for building facade materials Tay, Hui Xin Tiong Lee Kong, Robert School of Civil and Environmental Engineering CLKTIONG@ntu.edu.sg Engineering::Civil engineering Artificial Intelligence (AI) has been a popular topic in this age of technology. In the construction industry, it plays an vital role in improving the productivity and efficiency of work. This paper focuses on the development of an automated crack detection system using AI technology. The purpose is to improve the façade inspection and to increase the effectiveness in image analysis of defects. In the proposed method, classification and segmentation models are used to detect the presence of defects on building facades. The scope covers cracking and spalling on building facades in Singapore. Overall the result of the automated crack detection system developed achieves good performance with high accuracy result. To conclude, this is a significant finding in the construction field for future development and enhancement. Bachelor of Engineering (Civil) 2020-12-21T02:54:34Z 2020-12-21T02:54:34Z 2020 Final Year Project (FYP) https://hdl.handle.net/10356/145391 en application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Civil engineering |
spellingShingle |
Engineering::Civil engineering Tay, Hui Xin A study on methods and classification conditions for building facade materials |
description |
Artificial Intelligence (AI) has been a popular topic in this age of technology. In the construction industry, it plays an vital role in improving the productivity and efficiency of work. This paper focuses on the development of an automated crack detection system using AI technology. The purpose is to improve the façade inspection and to increase the effectiveness in image analysis of defects. In the proposed method, classification and segmentation models are used to detect the presence of defects on building facades. The scope covers cracking and spalling on building facades in Singapore. Overall the result of the automated crack detection system developed achieves good performance with high accuracy result. To conclude, this is a significant finding in the construction field for future development and enhancement. |
author2 |
Tiong Lee Kong, Robert |
author_facet |
Tiong Lee Kong, Robert Tay, Hui Xin |
format |
Final Year Project |
author |
Tay, Hui Xin |
author_sort |
Tay, Hui Xin |
title |
A study on methods and classification conditions for building facade materials |
title_short |
A study on methods and classification conditions for building facade materials |
title_full |
A study on methods and classification conditions for building facade materials |
title_fullStr |
A study on methods and classification conditions for building facade materials |
title_full_unstemmed |
A study on methods and classification conditions for building facade materials |
title_sort |
study on methods and classification conditions for building facade materials |
publisher |
Nanyang Technological University |
publishDate |
2020 |
url |
https://hdl.handle.net/10356/145391 |
_version_ |
1688654651643133952 |