Vision Measurement of Tunnel Structures with Robust Modelling and Deep Learning Algorithms
Abstract
1. Introduction
2. Measurement
3. Data Analysis
3.1. Robust 3D Modelling
3.2. Crack Analysis
4. Results
5. Discussion
6. Conclusions
- (i)
- A measurement of the tunnel structures is carried out with the vision-based method where ten cameras are installed in the vehicle and collect image data of the inner wall of the tunnel.
- (ii)
- The AI-based crack identification method is investigated in which deep learning based on CNN is employed.
- (iii)
- The 3D freeform surface is generated where the maximum likelihood function is applied to improve the robustness of the modelling.
- (iv)
- The global parameterization of the tunnel from images is computationally efficient, robust against disturbing data and convenient for visualization.
- (v)
- The robust model gains significant improvement compared to the least-squares model in terms of RMSE where the improvements in two segmentations are 429.32% and 425.06%.
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- Attard, L.; Debono, C.J.; Valentino, G.; Di Castro, M. Tunnel inspection using photogrammetric techniques and image processing: A review. ISPRS J. Photogramm. Remote Sens. 2018, 144, 180–188. [Google Scholar] [CrossRef]
- Cho, S.; Park, S.; Cha, G.; Oh, T. Development of image processing for crack detection on concrete structures through terrestrial laser scanning associated with the octree structure. Appl. Sci. 2018, 8, 2373. [Google Scholar] [CrossRef]
- Murakami, T.; Saito, N.; Komachi, Y.; Okamura, K.; Michikawa, T.; Sakashita, M.; Midorikawa, K. High Spatial Resolution Survey Using Frequency-Shifted Feedback Laser for Transport Infrastructure Maintenance. J. Disaster Res. 2017, 12, 546–556. [Google Scholar] [CrossRef]
- Afshanii, A.; Akagi, H.; Konishi, S. Investigate the detection rate of defects in concrete lining using infrared-thermography method. In Proceedings of the 7th China-Japan Geotechnical Symposium: New Advances in Geotechnical Engineering, Sanya, China, 16–18 March 2018; pp. 1–5. [Google Scholar]
- Daneshgaran, F.; Zacheo, L.; Stasio, F.D.; Mondin, M. Use of Deep Learning for Automatic Detection of Cracks in Tunnels: Prototype-2 Developed in the 2017–2018 Time Period. Transp. Res. Rec. 2019, 2673, 44–50. [Google Scholar] [CrossRef]
- Hirata, T.; Goda, Y.; Sakai, K.; Kiwa, T.; Adachi, S.; Tsukamoto, A.; Tsukada, K. Development of a Highly Sensitive Magnetic Field Detector With a Wide Frequency Range for Nondestructive Testing Using an HTS Coil With Magnetic Sensors. IEEE Trans. Appl. Supercond. 2019, 29, 1–5. [Google Scholar] [CrossRef]
- Loupos, K.; Doulamis, A.D.; Stentoumis, C.; Protopapadakis, E.; Makantasis, K.; Doulamis, N.D.; Menendez, E. Autonomous robotic system for tunnel structural inspection and assessment. Int. J. Intell. Robot. Appl. 2018, 2, 43–66. [Google Scholar] [CrossRef]
- Lee, J.S.; Hwang, S.H.; Choi, I.Y.; Choi, Y. Estimation of crack width based on shape-sensitive kernels and semantic segmentation. Struct. Control Health Monit. 2020, 24, e2504. [Google Scholar] [CrossRef]
- Medina, R.; Llamas, J.; Gómez-García-Bermejo, J.; Zalama, E.; Segarra, M.J. Crack detection in concrete tunnels using a Gabor filter invariant to rotation. Sensors 2017, 17, 1670. [Google Scholar] [CrossRef]
- Son, H.; Kim, C. Automatic segmentation and 3D modeling of pipelines into constituent parts from laser-scan data of the built environment. Autom. Constr. 2016, 68, 203–211. [Google Scholar] [CrossRef]
- Laefer, D.F.; Truong-Hong, L. Toward automatic generation of 3D steel structures for building information modelling. Autom. Constr. 2017, 74, 66–77. [Google Scholar] [CrossRef]
- Valero, E.; Adán, A.; Bosché, F. Semantic 3D reconstruction of furnished interiors using laser scanning and RFID technology. J. Comput. Civ. Eng. 2016, 30, 04015053. [Google Scholar] [CrossRef]
- Ullah, A.M.M.; Watanabe, M.; Kubo, A. Analytical Point-Cloud Based Geometric Modeling for Additive Manufacturing and Its Application to Cultural Heritage Preservation. Appl. Sci. 2018, 8, 656. [Google Scholar]
- Jeon, J.; Jung, J.; Kim, J.; Lee, S. Semantic Reconstruction: Reconstruction of Semantically Segmented 3D Meshes via Volumetric Semantic Fusion. Comput. Graph. Forum 2018, 37, 25–35. [Google Scholar] [CrossRef]
- Yang, H.; Xu, X.; Kargoll, B.; Neumann, I. An automatic and intelligent optimal surface modeling method for composite tunnel structures. Compos. Struct. 2019, 208, 702–710. [Google Scholar] [CrossRef]
- Díaz-Vilariño, L.; Khoshelham, K.; Martínez-Sánchez, J.; Arias, P. 3D modeling of building indoor spaces and closed doors from imagery and point clouds. Sensors 2015, 15, 3491–3512. [Google Scholar] [CrossRef]
- Xu, X.; Kargoll, B.; Bureick, J.; Yang, H.; Alkhatib, H.; Neumann, I. TLS-based profile model analysis of major composite structures with robust B-spline method. Compos. Struct. 2019, 184, 814–820. [Google Scholar] [CrossRef]
- Yang, H.; Xu, X.; Neumann, I. Optimal finite element model with response surface methodology for concrete structures based on Terrestrial Laser Scanning technology. Compos. Struct. 2018, 183, 2–6. [Google Scholar] [CrossRef]
- Xu, X.; Yang, H.; Zhang, Y.; Neumann, I. Intelligent 3D data extraction method for deformation analysis of composite structures. Compos. Struct. 2018, 203, 254–258. [Google Scholar] [CrossRef]
- Yang, H.; Xu, X.; Neumann, I. Laser Scanning-Based Updating of a Finite-Element Model for Structural Health Monitoring. IEEE Sens. 2016, 16, 2100–2104. [Google Scholar] [CrossRef]
- Xu, X.; Bureick, J.; Yang, H.; Neumann, I. TLS-based composite structure deformation analysis validated with laser tracker. Compos. Struct. 2018, 202, 60–65. [Google Scholar] [CrossRef]
- Yang, H.; Xu, X. Multi-sensor technology for B-spline modelling and deformation analysis of composite structures. Compos. Struct. 2019, 224, 111000. [Google Scholar] [CrossRef]
- Yang, H.; Xu, X.; Xu, W.; Neumann, I. Terrestrial Laser Scanning-Based Deformation Analysis for Arch and Beam Structures. IEEE Sens. J. 2017, 17, 4605–4611. [Google Scholar] [CrossRef]
- Wiśniewski, Z.; Kamiński, W. Estimation and Prediction of Vertical Deformations of Random Surfaces, Applying the Total Least Squares Collocation Method. Sensors 2020, 20, 3913. [Google Scholar] [CrossRef] [PubMed]
- Ziolkowski, P.; Szulwic, J.; Miskiewicz, M. Deformation Analysis of a Composite Bridge during Proof Loading Using Point Cloud Processing. Sensors 2018, 18, 4332. [Google Scholar] [CrossRef]
- Barazzetti, L.; Scaioni, M. Development and Implementation of Image-based Algorithms for Measurement of Deformations in Material Testing. Sensors 2010, 10, 7469–7495. [Google Scholar] [CrossRef]
- Piegl, L.; Tiller, W. The NURBS Book, 2nd ed.; Springer: Berlin, Germany; New York, NY, USA, 1997. [Google Scholar]
- Koch, K.; Kargoll, B. Expectation maximization algorithm for the variance-inflation model by applying the t-distribution. J. Appl. Geod. 2013, 7, 217–225. [Google Scholar] [CrossRef]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [Google Scholar]
- Gibert, X.; Patel, V.M.; Chellappa, R. Deep multitask learning for railway track inspection. Ieee Trans. Intell. Transp. Syst. 2016, 18, 153–164. [Google Scholar] [CrossRef]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 7–13 December 2015; pp. 1026–1034. [Google Scholar]
Layer Name | Details | Output |
---|---|---|
conv1 | 7 × 7, 64, stride 2 | 112 × 112 |
conv2_x | 3 × 3 max pooling, stride 2 | 56 × 56 |
conv3_x | 28 × 28 | |
conv4_x | 14 × 14 | |
conv5_x | 7 × 7 | |
Average pooling + Fully connected layer | 1 × 1 |
Model/Point Cloud Datasets | Segmentation 1 | Segmentation 2 |
---|---|---|
Least-squares Model | 18.95 | 23.26 |
Robust Model | 3.58 | 4.43 |
RMSE improvement | 429.32% | 425.06% |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Xu, X.; Yang, H. Vision Measurement of Tunnel Structures with Robust Modelling and Deep Learning Algorithms. Sensors 2020, 20, 4945. https://doi.org/10.3390/s20174945
Xu X, Yang H. Vision Measurement of Tunnel Structures with Robust Modelling and Deep Learning Algorithms. Sensors. 2020; 20(17):4945. https://doi.org/10.3390/s20174945
Chicago/Turabian StyleXu, Xiangyang, and Hao Yang. 2020. "Vision Measurement of Tunnel Structures with Robust Modelling and Deep Learning Algorithms" Sensors 20, no. 17: 4945. https://doi.org/10.3390/s20174945
APA StyleXu, X., & Yang, H. (2020). Vision Measurement of Tunnel Structures with Robust Modelling and Deep Learning Algorithms. Sensors, 20(17), 4945. https://doi.org/10.3390/s20174945