Towards Automated 3D Inspection of Water Leakages in Shield Tunnel Linings Using Mobile Laser Scanning Data

Huang, Hongwei; Cheng, Wen; Zhou, Mingliang; Chen, Jiayao; Zhao, Shuai

doi:10.3390/s20226669

Cited by 57 publications

(26 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These equations are built under the assumption that the geometry of a tunnel can be modeled by a cylinder, and this assumption is valid because the deformation of a tunnel compared with the size of it is negligible. 51,55 The specific procedure of this warped method contains three steps. First, each pixel in the stitched image is converted to a point in the center of a grid of the custom 2D RGB point cloud (Figure 18).…”

Section: Image Mosaicingmentioning

confidence: 99%

“…In order to provide a larger field of 3D view, the image is warped according to the following equations:

x^{'} = ((), \frac{π}{2} - θ) \times R

y^{'} = y = H

z^{'} = R

θ = \frac{π}{2} - \frac{((), W - P / 2) \times A}{R}

where ( x ′, y ′, z ′) is the coordinate in Cartesian coordinates; ( H , W ) is the coordinate in image coordinates (Figure 17); P is the total number of pixels of the image along the W direction; A is the precision of pixel (0.3 mm/pixel in this study); and R is the inner radius of the tunnel lining. These equations are built under the assumption that the geometry of a tunnel can be modeled by a cylinder, and this assumption is valid because the deformation of a tunnel compared with the size of it is negligible 51,55 …”

Section: Image Mosaicingmentioning

confidence: 99%

“…First, each pixel in the stitched image is converted to a point in the center of a grid of the custom 2D RGB point cloud (Figure 18). Second, the two nearest neighboring points are connected to generate the 2D mesh using a diagonal mesh method, 55 as displayed in Figure 18. Finally, the 2D mesh is warped into a 3D shaped image following Equations 3a–3d.…”

Section: Image Mosaicingmentioning

confidence: 99%

See 2 more Smart Citations

Deep learning‐based classification and instance segmentation of leakage‐area and scaling images of shield tunnel linings

Zhao

Shadabfar

Zhang

et al. 2021

Struct Control Health Monit

Self Cite

View full text Add to dashboard Cite

This paper presents an approach for the integrated process of classification and instance segmentation of leakage-area and scaling images from shield tunnel linings. For this purpose, the previously established dataset of leakage-area images by the authors is enlarged by means of adding scaling ones. Afterwards, data augmentation is implemented to enrich the database in the classification dataset, and the augmented classification dataset contains 5776 images. The instance segmentation dataset is subsequently enlarged through original images without any data augmentation, including 1496 images. Then a residual net with 101 layers (i.e., ResNet-101) is applied to the classification dataset to obtain a model that can identify leakage-area and scaling images from those of shield tunnel linings. The ResNet-101 classification model achieves an accuracy of 93.37% in terms of testing classification dataset. Moreover, a mask region-based convolutional neural network (Mask R-CNN) is utilized to perform instance segmentation of leakage areas and scaling in the images classified by the ResNet-101 model. The segmentation results of the Mask R-CNN model show 96.1% and 95.6% average precision (AP) with intersection over union (IoU) of 0.5 for bounding box and mask predication, respectively. By using the proposed approach, the leakage-area and scaling defects can be automatically classified and quantified with an overall accuracy of 89.3%, which is quite promising compared to the inherent uncertainty in geotechnical engineering. Image mosaicing is finally applied to provide inspectors with the intuitive observation of the location and distribution information of defects on the tunnel lining.

show abstract

Section: Image Mosaicingmentioning

confidence: 99%

“…In order to provide a larger field of 3D view, the image is warped according to the following equations:

x^{'} = ((), \frac{π}{2} - θ) \times R

y^{'} = y = H

z^{'} = R

θ = \frac{π}{2} - \frac{((), W - P / 2) \times A}{R}

Section: Image Mosaicingmentioning

confidence: 99%

Section: Image Mosaicingmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning‐based classification and instance segmentation of leakage‐area and scaling images of shield tunnel linings

Zhao

Shadabfar

Zhang

et al. 2021

Struct Control Health Monit

Self Cite

View full text Add to dashboard Cite

show abstract

“…Sensors 2021, 21, x FOR PEER REVIEW 21 of 25 et al [55]), the area, and the volume of the identified spalling defect are accurately quantified and outputted. This automated spalling inspection approach can significantly aid with tunnel structural health monitoring and improve the digital management of railway tunnels.…”

Section: Discussionmentioning

confidence: 99%

A Novel Approach to Automated 3D Spalling Defects Inspection in Railway Tunnel Linings Using Laser Intensity and Depth Information

Zhou

Cheng

Huang

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

The detection of concrete spalling is critical for tunnel inspectors to assess structural risks and guarantee the daily operation of the railway tunnel. However, traditional spalling detection methods mostly rely on visual inspection or camera images taken manually, which are inefficient and unreliable. In this study, an integrated approach based on laser intensity and depth features is proposed for the automated detection and quantification of concrete spalling. The Railway Tunnel Spalling Defects (RTSD) database, containing intensity images and depth images of the tunnel linings, is established via mobile laser scanning (MLS), and the Spalling Intensity Depurator Network (SIDNet) model is proposed for automatic extraction of the concrete spalling features. The proposed model is trained, validated and tested on the established RSTD dataset with impressive results. Comparison with several other spalling detection models shows that the proposed model performs better in terms of various indicators such as MPA (0.985) and MIoU (0.925). The extra depth information obtained from MLS allows for the accurate evaluation of the volume of detected spalling defects, which is beyond the reach of traditional methods. In addition, a triangulation mesh method is implemented to reconstruct the 3D tunnel lining model and visualize the 3D inspection results. As a result, a 3D inspection report can be outputted automatically containing quantified spalling defect information along with relevant spatial coordinates. The proposed approach has been conducted on several railway tunnels in Yunnan province, China and the experimental results have proved its validity and feasibility.

show abstract

“…Containing a large quantity of joints, holes and other weak points, shield tunnels are very likely to encounter the hazards of sand gushing and water leakage, especially for tunnels in water-rich sandy stratum [1,2]. These hazards could affect the normal operation of the tunnel, or even endanger the safety of the tunnel structure, and cause engineering accidents [3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Simulating water and soil gushing around shield tunnel with Material Point Method

Xiaochuang¹,

Ceccato²,

Zhang³

et al. 2021

9th Edition of the International Conference on Computational Methods for Coupled Problems in Science and Engineering

View full text Add to dashboard Cite

In recent years, serious accidents due to sand and water gushing around shield tunnel happen from time to time. Sand and water gushing could lead to large soil displacement, change soil stress field around tunnels, and then threaten the safety of tunnel structures. To date, there is a lack of theoretical research on the evolution of sand and water gushing, and the numerical simulation of the process is challenging because soil-water interaction, soil-structure interaction and large deformations have to be accounted for. In this paper, the Material Point Method (MPM) is used to deal with large deformation and various simulation cases considering different gushing locations at tunnels are carried out to investigate the development of soil displacement and stress around tunnels due to water and soil gushing. The results show that position of the gushing point greatly affect the damage scope. The sand gushing rate, the soil displacement and stress field, the ground settlement trough, and the earth pressure on the tunnel linings develop completely differently due to the varying position of the gushing point, which are analyzed to suggest reasonable guidance and countermeasures for preventing future sand and water gushing accidents.

show abstract

Towards Automated 3D Inspection of Water Leakages in Shield Tunnel Linings Using Mobile Laser Scanning Data

Cited by 57 publications

References 50 publications

Deep learning‐based classification and instance segmentation of leakage‐area and scaling images of shield tunnel linings

Deep learning‐based classification and instance segmentation of leakage‐area and scaling images of shield tunnel linings

A Novel Approach to Automated 3D Spalling Defects Inspection in Railway Tunnel Linings Using Laser Intensity and Depth Information

Simulating water and soil gushing around shield tunnel with Material Point Method

Contact Info

Product

Resources

About