Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/221796
Title: CREATION OF BIM FROM POINT CLOUD DATA USING AI TECHNIQUES
Authors: TEO SHU ZHAO
Keywords: 2020-2021
Building
Bachelor's
BACHELOR OF SCIENCE (PROJECT AND FACILITIES MANAGEMENT)
Wang Qian
PFM
Issue Date: 31-May-2021
Citation: TEO SHU ZHAO (2021-05-31). CREATION OF BIM FROM POINT CLOUD DATA USING AI TECHNIQUES. ScholarBank@NUS Repository.
Abstract: Building Information Models (BIMs) are three-dimensional (3D) illustrations of a structure and have been increasing employed to assist through the life cycle of a building, from the construction phase to the operations and maintenance phase after the building is completed. It is widely understood that during the construction phase, there are discrepancies between the present constructed state of a structure, known as the “as-built” state, and the structure “as-designed” specifications stated in the contractual documents. This is due the presence of real-life scenarios such as omission in the design or poor workmanship. As such, it is crucial to capture the as-built state of the structure in 3D BIM. At the same time, the 3D reconstruction of as-built buildings is known to take up significant amount of time and being a tedious process, requiring well-trained personnel to carry out. Hence, research have dived into how to automate the steps to be taken from the acquisition of as-built data as a 3D point cloud into 3D BIM, even with the utilization of machine learning to lower the barriers for such tasks. This paper breaks down the process to be undertaken from the acquisition of data points for the 3D point cloud data to the reconstruction of the as-built state of the structure in 3D BIM. Proposed approaches to automate such processes will be reviewed, compiling different methodologies taken, and propose possible research directions in the construction sector.
URI: https://scholarbank.nus.edu.sg/handle/10635/221796
Appears in Collections:Bachelor's Theses

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Teo Shu Zhao 2020-2021_dissertation.pdf357.38 kBAdobe PDF

RESTRICTED

NoneLog In

Page view(s)

20
checked on Nov 17, 2022

Download(s)

7
checked on Nov 17, 2022

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.