Automatic 3D Reconstruction for As-built Underground Utilities

This thesis addresses three challenges in the 3D reconstruction of underground utilities. Firstly, it introduces a high-precision ground penetrating radar-based deep learning model to enhance localization accuracy. Secondly, it presents an unsupervised deep learning model for effective 3D reconstruc...

Full description

Bibliographic Details
Main Author: Su, Yang
Format: Thesis
Published: Curtin University 2024
Online Access:http://hdl.handle.net/20.500.11937/96628
_version_ 1848766183282573312
author Su, Yang
author_facet Su, Yang
author_sort Su, Yang
building Curtin Institutional Repository
collection Online Access
description This thesis addresses three challenges in the 3D reconstruction of underground utilities. Firstly, it introduces a high-precision ground penetrating radar-based deep learning model to enhance localization accuracy. Secondly, it presents an unsupervised deep learning model for effective 3D reconstruction under low-light conditions. Finally, it proposes a graph convolutional network-based model to accurately complete missing topological data of utility networks. Experimental results demonstrate significant improvements in accuracy, speed, and data integrity.
first_indexed 2025-11-14T11:47:05Z
format Thesis
id curtin-20.500.11937-96628
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:47:05Z
publishDate 2024
publisher Curtin University
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-966282024-12-20T01:43:44Z Automatic 3D Reconstruction for As-built Underground Utilities Su, Yang This thesis addresses three challenges in the 3D reconstruction of underground utilities. Firstly, it introduces a high-precision ground penetrating radar-based deep learning model to enhance localization accuracy. Secondly, it presents an unsupervised deep learning model for effective 3D reconstruction under low-light conditions. Finally, it proposes a graph convolutional network-based model to accurately complete missing topological data of utility networks. Experimental results demonstrate significant improvements in accuracy, speed, and data integrity. 2024 Thesis http://hdl.handle.net/20.500.11937/96628 Curtin University fulltext
spellingShingle Su, Yang
Automatic 3D Reconstruction for As-built Underground Utilities
title Automatic 3D Reconstruction for As-built Underground Utilities
title_full Automatic 3D Reconstruction for As-built Underground Utilities
title_fullStr Automatic 3D Reconstruction for As-built Underground Utilities
title_full_unstemmed Automatic 3D Reconstruction for As-built Underground Utilities
title_short Automatic 3D Reconstruction for As-built Underground Utilities
title_sort automatic 3d reconstruction for as-built underground utilities
url http://hdl.handle.net/20.500.11937/96628