TUC-Net: A Point Cloud Segmentation Network Based on Neighborhood Feature Perception Aggregation for Tunnels Under Construction
Guardado en:
| Publicado en: | IEEE Transactions on Intelligent Transportation Systems vol. 26, no. 12 (2025), p. 10048-10066 |
|---|---|
| Autor principal: | |
| Otros Autores: | , , , , |
| Publicado: |
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
|
| Materias: | |
| Acceso en línea: | Citation/Abstract |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3226499598 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 1524-9050 | ||
| 022 | |a 1558-0016 | ||
| 024 | 7 | |a 10.1109/TITS.2025.3542500 |2 doi | |
| 035 | |a 3226499598 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 121629 |2 nlm | ||
| 100 | 1 | |a Zhang, Xing |u School of Architecture and Urban Planning, Guangdong Key Laboratory of Urban Informatics, the MNR Key Laboratory for Geo-Environmental Monitoring of Great Bay Area, and Shenzhen Key Laboratory of Spatial Information Smart Sensing and Services, Shenzhen University, Shenzhen, China | |
| 245 | 1 | |a TUC-Net: A Point Cloud Segmentation Network Based on Neighborhood Feature Perception Aggregation for Tunnels Under Construction | |
| 260 | |b The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a The high risks in tunnel construction underscore the critical necessity for intelligent tunnel construction. Unmanned tunnel data collection is vital for intelligent construction; additionally, semantic segmentation aids in understanding the environment. However, complex tunnel terrains are challenging for three-dimensional (3D) laser scanning, and diverse interior structures and nontunnel elements complicate accurate segmentation by subsequent networks. Therefore, this paper proposed a tunnel mobile 3D mapping system (TMMS) for complex terrain in construction tunnels using a quadruped robot and simultaneous localization and mapping (SLAM). Additionally, a deep learning-based semantic segmentation network (TUC-Net) is proposed for analysing 3D point clouds in tunnels under construction. The research presented the neighbourhood feature perception enhancement (NFPE) module to enhance the representation of local features, introduce a self-attention (SA) module and improve the loss function to improve network accuracy. The NFPE module enhances feature aggregation for unstructured objects, and the SA module improves the learning of global features, critical for tunnel point cloud segmentation. The TMMS is used to collect point cloud data from tunnels under construction, leading to the creation of the tunnels under construction point clouds (TUCPC) dataset for training and evaluating the TUC-Net network. Compared to other 3D point cloud semantic segmentation methods, the proposed method demonstrated superior performance, achieving an overall accuracy (OA) of 99.45% and a mean intersection over union (mIoU) of 94.06%, surpassing that of other methods by at least 4.41%. In addition, ablation studies were also performed on the NFPE and SA modules to validate their efficacy. | |
| 653 | |a Perception | ||
| 653 | |a Construction | ||
| 653 | |a Simultaneous localization and mapping | ||
| 653 | |a Semantic segmentation | ||
| 653 | |a Modules | ||
| 653 | |a Deep learning | ||
| 653 | |a Image segmentation | ||
| 653 | |a Tunnel construction | ||
| 653 | |a Data collection | ||
| 653 | |a Ablation | ||
| 653 | |a Semantics | ||
| 653 | |a Three dimensional models | ||
| 700 | 1 | |a Huang, Xinglin |u School of Architecture and Urban Planning, Guangdong Key Laboratory of Urban Informatics, the MNR Key Laboratory for Geo-Environmental Monitoring of Great Bay Area, and Shenzhen Key Laboratory of Spatial Information Smart Sensing and Services, Shenzhen University, Shenzhen, China | |
| 700 | 1 | |a Hong, Kaipeng |u School of Architecture and Urban Planning, Guangdong Key Laboratory of Urban Informatics, the MNR Key Laboratory for Geo-Environmental Monitoring of Great Bay Area, and Shenzhen Key Laboratory of Spatial Information Smart Sensing and Services, Shenzhen University, Shenzhen, China | |
| 700 | 1 | |a Li, Qingquan |u College of Civil and Transportation Engineering, Guangdong Key Laboratory of Urban Informatics, the MNR Key Laboratory for Geo-Environmental Monitoring of Great Bay Area, Shenzhen Key Laboratory of Spatial Smart Sensing and Services, and Guangdong Laboratory of Artificial Intelligence and Digital Economy, Shenzhen University, Shenzhen, China | |
| 700 | 1 | |a Wang, Ruisheng |u School of Architecture and Urban Planning, Guangdong-Hong Kong-Macau Joint Laboratory for Smart Cities, Shenzhen University, Shenzhen, China | |
| 700 | 1 | |a Zhou, Baoding |u College of Civil and Transportation Engineering, Institute of Urban Smart Transportation and Safety Maintenance, Shenzhen University, Shenzhen, China | |
| 773 | 0 | |t IEEE Transactions on Intelligent Transportation Systems |g vol. 26, no. 12 (2025), p. 10048-10066 | |
| 786 | 0 | |d ProQuest |t Advanced Technologies & Aerospace Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3226499598/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |