Automatic 3D Reconstruction for As-built Underground Utilities
dc.contributor.author | Su, Yang | |
dc.contributor.supervisor | Brad Carey | en_US |
dc.contributor.supervisor | Peng Wu | en_US |
dc.contributor.supervisor | Jun Wang | en_US |
dc.date.accessioned | 2024-12-20T01:43:08Z | |
dc.date.available | 2024-12-20T01:43:08Z | |
dc.date.issued | 2024 | en_US |
dc.identifier.uri | http://hdl.handle.net/20.500.11937/96628 | |
dc.description.abstract |
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. | en_US |
dc.publisher | Curtin University | en_US |
dc.title | Automatic 3D Reconstruction for As-built Underground Utilities | en_US |
dc.type | Thesis | en_US |
dcterms.educationLevel | PhD | en_US |
curtin.department | School of Design and the Built Environment | en_US |
curtin.accessStatus | Open access | en_US |
curtin.faculty | Humanities | en_US |
curtin.contributor.orcid | Su, Yang [0000-0002-6290-2128] | en_US |