journal article·2021-01

Structural displacement monitoring based on mask regions with convolutional neural network

Yang Zhang, Peng Liu, Xuefeng Zhao

Publisher page

Abstract

Abstract Displacement monitoring is an important part of structural health monitoring. This paper proposes a structural displacement monitoring method based on mask regions with convolutional neural network (Mask R-CNN), which combines deep learning with machine vision to extract the coordinates of calibration object. First, a calibration object dataset was collected. The dataset contains 165 images. Second, the dataset was trained by Mask R-CNN to obtain a monitoring model, which can generate a mask to cover the calibration object in the image. Third, the mask information is extracted from the image to obtain the coordinates of calibration object. Finally, the structure displacement can be obtained by the coordinates. In this paper, the method is applied to the static displacement monitoring and dynamic displacement monitoring. The results showed that average error of static displacement monitoring is 2.05%, and the correlation coefficient between monitoring results of the proposed method and laser displacement sensor monitoring results is as high as 0.9836 in dynamic displacement monitoring. To solve the problem of remote displacement monitoring, a telephoto lens was mounted on a smartphone to monitor displacement of 10 m distance. The results showed that the average error of remote displacement monitoring is 4.18%.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Infrastructure Maintenance and Monitoring · Structural Health Monitoring Techniques · Industrial Vision Systems and Defect Detection

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (29)

Show source-provided references
1. Structural health monitoring: closing the gap between research and industrial deployment10.1177/1475921717750047 ↗
2. On switching response surface models, with applications to the structural health monitoring of bridges10.1016/j.ymssp.2017.04.022 ↗
3. Radar-based structural health monitoring of wind turbine blades: the case of damage localization: radar-based structural health monitoring of wind turbine blades: the case of damage localization10.1002/we.2184 ↗
4. IFC monitor – an IFC schema extension for modeling structural health monitoring systems10.1016/j.aei.2018.04.011 ↗
5. A variable-frequency structural health monitoring system based on omnidirectional shear horizontal wave piezoelectric transducers10.1088/1361-665X/aaa207 ↗
6. Visual-inertial displacement sensing using data fusion of vision-based displacement with acceleration10.1002/stc.2122 ↗
7. Omidalizarandi, Mohammad, et al. Accurate vision-based displacement and vibration analysis of bridge structures by means of an image-assisted total station. Adv. Mech. Eng. 10.6 (2018): 1687814018780052.10.1177/1687814018780052 ↗
8. Structural displacement estimation through multi-rate fusion of accelerometer and RTK-GPS displacement and velocity measurements10.1016/j.measurement.2018.07.090 ↗
9. A non-contact vision-based system for multipoint displacement monitoring in a cable-stayed footbridge10.1002/stc.2155 ↗
10. Displacement monitoring for slope stability evaluation based on binocular vision systems10.1016/j.ijleo.2018.06.097 ↗
11. Development and field testing of a vision-based displacement system using a low cost wireless action camera10.1016/j.ymssp.2018.11.015 ↗
12. Vision-based displacement sensor for monitoring dynamic response using robust object search algorithm10.1109/JSEN.2013.2273309 ↗
13. Adaptive document image binarization10.1016/S0031-3203(99)00055-2 ↗
14. Adaptive degraded document image binarization10.1016/j.patcog.2005.09.010 ↗
15. Study and comparison of various image edge detection techniques
16. Image selective smoothing and edge detection by nonlinear diffusion10.1137/0729012 ↗
17. Deep architecture for traffic flow prediction: deep belief networks with multitask learning10.1109/TITS.2014.2311123 ↗
18. Van der Pol, Elise, and Frans A. Oliehoek. Coordinated deep reinforcement learners for traffic light control. Proceedings of Learning, Inference and Control of Multi-Agent Systems (at NIPS 2016) (2016).
19. R. Vinayakumar, K.P. Soman, Prabaharan Poornachandran. “Applying deep learning approaches for network traffic prediction.” 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, 2017.10.1109/ICACCI.2017.8126198 ↗
20. Optimized structure of the traffic flow forecasting model with a deep learning approach10.1109/TNNLS.2016.2574840 ↗
21. Deep learning in medical image analysis10.1146/annurev-bioeng-071516-044442 ↗
22. Deep learning in drug discovery10.1002/minf.201501008 ↗
23. Bolt loosening angle detection technology using deep learning10.1002/stc.2292 ↗
24. Autonomous bolt loosening detection using deep learning10.1177/1475921719837509 ↗
25. Girshick, Ross, et al. Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition. 2014.10.1109/CVPR.2014.81 ↗
26. Girshick, Ross. “Fast r-cnn.” Proceedings of the IEEE international conference on computer vision. 2015.10.1109/ICCV.2015.169 ↗
27. Ren, Shaoqing, et al. “Faster r-cnn: Towards real-time object detection with region proposal networks.” Advances in neural information processing systems. 2015.
28. He, Kaiming, et al. “Mask r-cnn.” Proceedings of the IEEE international conference on computer vision. 2017.10.1109/ICCV.2017.322 ↗
29. Long, Jonathan, Evan Shelhamer, and Trevor Darrell. “Fully convolutional networks for semantic segmentation.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.10.1109/CVPR.2015.7298965 ↗