Domain knowledge-enhanced region growing framework for semantic segmentation of bridge point clouds
Utilising domain knowledge (DK) to semantically segment bridge point clouds has attracted growing research interest. However, current approaches are often tailored to specific bridges, limiting their general applicability. To address this problem, this paper introduces a DK-enhanced Region Growing (...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/179996 |
| _version_ | 1811676383543296000 |
|---|---|
| author | Yang, Tao Zou, Yang Yang, Xiaofei del Rey Castillo, Enrique |
| author2 | School of Civil and Environmental Engineering |
| author_facet | School of Civil and Environmental Engineering Yang, Tao Zou, Yang Yang, Xiaofei del Rey Castillo, Enrique |
| author_sort | Yang, Tao |
| collection | NTU |
| description | Utilising domain knowledge (DK) to semantically segment bridge point clouds has attracted growing research interest. However, current approaches are often tailored to specific bridges, limiting their general applicability. To address this problem, this paper introduces a DK-enhanced Region Growing (DKRG) framework for point cloud semantic segmentation of reinforced concrete (RC) girder bridges. Inspired by the vertical layout characteristics of bridges, the generation of DK-based point features from Finite Element Analysis (FEA) is first proposed. Then, DKRG is employed to segment bridge components from substructures to superstructures by leveraging an “easy-to-difficult” strategy. Validation results demonstrate the effectiveness of our method, achieving the lowest mean Intersection over Union (mIoU) of 95.47% for the entire bridge and 93.44% for different component types. This study provides a new DK-based framework for semantic segmentation of RC girder bridges and sheds new light on using FEA-generated point features. |
| first_indexed | 2024-10-01T02:20:36Z |
| format | Journal Article |
| id | ntu-10356/179996 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:20:36Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1799962024-09-13T15:33:41Z Domain knowledge-enhanced region growing framework for semantic segmentation of bridge point clouds Yang, Tao Zou, Yang Yang, Xiaofei del Rey Castillo, Enrique School of Civil and Environmental Engineering Engineering Point cloud Semantic segmentation Utilising domain knowledge (DK) to semantically segment bridge point clouds has attracted growing research interest. However, current approaches are often tailored to specific bridges, limiting their general applicability. To address this problem, this paper introduces a DK-enhanced Region Growing (DKRG) framework for point cloud semantic segmentation of reinforced concrete (RC) girder bridges. Inspired by the vertical layout characteristics of bridges, the generation of DK-based point features from Finite Element Analysis (FEA) is first proposed. Then, DKRG is employed to segment bridge components from substructures to superstructures by leveraging an “easy-to-difficult” strategy. Validation results demonstrate the effectiveness of our method, achieving the lowest mean Intersection over Union (mIoU) of 95.47% for the entire bridge and 93.44% for different component types. This study provides a new DK-based framework for semantic segmentation of RC girder bridges and sheds new light on using FEA-generated point features. Published version The authors would like to acknowledge the financial support from the University of Auckland and China Scholarship Council (Project No. 202206690016). 2024-09-09T05:11:56Z 2024-09-09T05:11:56Z 2024 Journal Article Yang, T., Zou, Y., Yang, X. & del Rey Castillo, E. (2024). Domain knowledge-enhanced region growing framework for semantic segmentation of bridge point clouds. Automation in Construction, 165, 105572-. https://dx.doi.org/10.1016/j.autcon.2024.105572 0926-5805 https://hdl.handle.net/10356/179996 10.1016/j.autcon.2024.105572 2-s2.0-85196188468 165 105572 en Automation in Construction © 2024 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). application/pdf |
| spellingShingle | Engineering Point cloud Semantic segmentation Yang, Tao Zou, Yang Yang, Xiaofei del Rey Castillo, Enrique Domain knowledge-enhanced region growing framework for semantic segmentation of bridge point clouds |
| title | Domain knowledge-enhanced region growing framework for semantic segmentation of bridge point clouds |
| title_full | Domain knowledge-enhanced region growing framework for semantic segmentation of bridge point clouds |
| title_fullStr | Domain knowledge-enhanced region growing framework for semantic segmentation of bridge point clouds |
| title_full_unstemmed | Domain knowledge-enhanced region growing framework for semantic segmentation of bridge point clouds |
| title_short | Domain knowledge-enhanced region growing framework for semantic segmentation of bridge point clouds |
| title_sort | domain knowledge enhanced region growing framework for semantic segmentation of bridge point clouds |
| topic | Engineering Point cloud Semantic segmentation |
| url | https://hdl.handle.net/10356/179996 |
| work_keys_str_mv | AT yangtao domainknowledgeenhancedregiongrowingframeworkforsemanticsegmentationofbridgepointclouds AT zouyang domainknowledgeenhancedregiongrowingframeworkforsemanticsegmentationofbridgepointclouds AT yangxiaofei domainknowledgeenhancedregiongrowingframeworkforsemanticsegmentationofbridgepointclouds AT delreycastilloenrique domainknowledgeenhancedregiongrowingframeworkforsemanticsegmentationofbridgepointclouds |