Enhanced Water Leakage Detection in Shield Tunnels Based on Laser Scanning Intensity Images Using RDES-Net
Tunnel water leakage detection is the difficulty and bottleneck in shield tunnel operation monitoring. This article introduces the RDES method for detecting water leakage in shield tunnels. First, to enhance the model's information extraction capabilities, we introduce a detection-efficie...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10433558/ |
| _version_ | 1797269136481452032 |
|---|---|
| author | Zhaojie Guo Jifan Wei Haili Sun Ruofei Zhong Changqi Ji |
| author_facet | Zhaojie Guo Jifan Wei Haili Sun Ruofei Zhong Changqi Ji |
| author_sort | Zhaojie Guo |
| collection | DOAJ |
| description | Tunnel water leakage detection is the difficulty and bottleneck in shield tunnel operation monitoring. This article introduces the RDES method for detecting water leakage in shield tunnels. First, to enhance the model's information extraction capabilities, we introduce a detection-efficient efficient 3 normalized conv1ds of attention module by combining the characteristics of the attention mechanisms, efficient channel attention, and coordinate attention. This module aims to focus the model's backbone network on capturing the spatial features of water leakage data and facilitating meaningful interaction between different channels. In addition, we design the residual deformable convolution to provide the convolutional energy with the flexibility to detect deformed targets, thereby enhancing the model's recognition ability. Finally, we incorporate a nonmaximum suppression technique during prediction to improve detection accuracy. This technique retains more bounding boxes by applying soft-NMS weighted averaging. The results of the measured and publicly available data show that the RDES algorithm outperforms all the compared algorithms and is advanced and efficient. The results show that compared with the baseline, the RDES algorithm improves the <italic>F</italic>1 metrics, mAP0.5, mAP0.75, and mAP by 2.2%, 4.4%, 9.2%, and 5.2% on the laser intensity image dataset, and by 3.1%, 4.6%, 7.9%, and 5.9% on the optical image dataset. |
| first_indexed | 2024-03-07T14:05:18Z |
| format | Article |
| id | doaj.art-c5873108b3d845bdb8770f559b8e586d |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-25T01:43:35Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-c5873108b3d845bdb8770f559b8e586d2024-03-08T00:00:10ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-01175680569010.1109/JSTARS.2024.336553510433558Enhanced Water Leakage Detection in Shield Tunnels Based on Laser Scanning Intensity Images Using RDES-NetZhaojie Guo0https://orcid.org/0009-0001-4033-9098Jifan Wei1https://orcid.org/0009-0003-6423-2046Haili Sun2https://orcid.org/0000-0002-0653-3225Ruofei Zhong3https://orcid.org/0000-0002-6064-4479Changqi Ji4School of Resources and Environment, Capital Normal University, Beijing, ChinaSchool of Resources and Environment, Capital Normal University, Beijing, ChinaKey Laboratory of 3D Information Acquisition and Application, Ministry of Education, Capital Normal University, Beijing, ChinaKey Laboratory of 3D Information Acquisition and Application, Ministry of Education, Capital Normal University, Beijing, ChinaSchool of Resources and Environment, Capital Normal University, Beijing, ChinaTunnel water leakage detection is the difficulty and bottleneck in shield tunnel operation monitoring. This article introduces the RDES method for detecting water leakage in shield tunnels. First, to enhance the model's information extraction capabilities, we introduce a detection-efficient efficient 3 normalized conv1ds of attention module by combining the characteristics of the attention mechanisms, efficient channel attention, and coordinate attention. This module aims to focus the model's backbone network on capturing the spatial features of water leakage data and facilitating meaningful interaction between different channels. In addition, we design the residual deformable convolution to provide the convolutional energy with the flexibility to detect deformed targets, thereby enhancing the model's recognition ability. Finally, we incorporate a nonmaximum suppression technique during prediction to improve detection accuracy. This technique retains more bounding boxes by applying soft-NMS weighted averaging. The results of the measured and publicly available data show that the RDES algorithm outperforms all the compared algorithms and is advanced and efficient. The results show that compared with the baseline, the RDES algorithm improves the <italic>F</italic>1 metrics, mAP0.5, mAP0.75, and mAP by 2.2%, 4.4%, 9.2%, and 5.2% on the laser intensity image dataset, and by 3.1%, 4.6%, 7.9%, and 5.9% on the optical image dataset.https://ieeexplore.ieee.org/document/10433558/Efficient 3 normalized Conv1ds of attention (E3NCA)laser intensity imageobject detectionresidual deformable (RD2)water leakage detection |
| spellingShingle | Zhaojie Guo Jifan Wei Haili Sun Ruofei Zhong Changqi Ji Enhanced Water Leakage Detection in Shield Tunnels Based on Laser Scanning Intensity Images Using RDES-Net IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Efficient 3 normalized Conv1ds of attention (E3NCA) laser intensity image object detection residual deformable (RD2) water leakage detection |
| title | Enhanced Water Leakage Detection in Shield Tunnels Based on Laser Scanning Intensity Images Using RDES-Net |
| title_full | Enhanced Water Leakage Detection in Shield Tunnels Based on Laser Scanning Intensity Images Using RDES-Net |
| title_fullStr | Enhanced Water Leakage Detection in Shield Tunnels Based on Laser Scanning Intensity Images Using RDES-Net |
| title_full_unstemmed | Enhanced Water Leakage Detection in Shield Tunnels Based on Laser Scanning Intensity Images Using RDES-Net |
| title_short | Enhanced Water Leakage Detection in Shield Tunnels Based on Laser Scanning Intensity Images Using RDES-Net |
| title_sort | enhanced water leakage detection in shield tunnels based on laser scanning intensity images using rdes net |
| topic | Efficient 3 normalized Conv1ds of attention (E3NCA) laser intensity image object detection residual deformable (RD2) water leakage detection |
| url | https://ieeexplore.ieee.org/document/10433558/ |
| work_keys_str_mv | AT zhaojieguo enhancedwaterleakagedetectioninshieldtunnelsbasedonlaserscanningintensityimagesusingrdesnet AT jifanwei enhancedwaterleakagedetectioninshieldtunnelsbasedonlaserscanningintensityimagesusingrdesnet AT hailisun enhancedwaterleakagedetectioninshieldtunnelsbasedonlaserscanningintensityimagesusingrdesnet AT ruofeizhong enhancedwaterleakagedetectioninshieldtunnelsbasedonlaserscanningintensityimagesusingrdesnet AT changqiji enhancedwaterleakagedetectioninshieldtunnelsbasedonlaserscanningintensityimagesusingrdesnet |