Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017 Jun 6;17(6):1305.
doi: 10.3390/s17061305.

A High-Speed Target-Free Vision-Based Sensor for Bus Rapid Transit Viaduct Vibration Measurements Using CMT and ORB Algorithms

Qijun Hu  1 , Songsheng He  2 , Shilong Wang  3 , Yugang Liu  4 , Zutao Zhang  5 , Leping He  6 , Fubin Wang  7 , Qijie Cai  8 , Rendan Shi  9 , Yuan Yang  10
Affiliations

A High-Speed Target-Free Vision-Based Sensor for Bus Rapid Transit Viaduct Vibration Measurements Using CMT and ORB Algorithms

Qijun Hu et al. Sensors (Basel). .

Abstract

Bus Rapid Transit (BRT) has become an increasing source of concern for public transportation of modern cities. Traditional contact sensing techniques during the process of health monitoring of BRT viaducts cannot overcome the deficiency that the normal free-flow of traffic would be blocked. Advances in computer vision technology provide a new line of thought for solving this problem. In this study, a high-speed target-free vision-based sensor is proposed to measure the vibration of structures without interrupting traffic. An improved keypoints matching algorithm based on consensus-based matching and tracking (CMT) object tracking algorithm is adopted and further developed together with oriented brief (ORB) keypoints detection algorithm for practicable and effective tracking of objects. Moreover, by synthesizing the existing scaling factor calculation methods, more rational approaches to reducing errors are implemented. The performance of the vision-based sensor is evaluated through a series of laboratory tests. Experimental tests with different target types, frequencies, amplitudes and motion patterns are conducted. The performance of the method is satisfactory, which indicates that the vision sensor can extract accurate structure vibration signals by tracking either artificial or natural targets. Field tests further demonstrate that the vision sensor is both practicable and reliable.

Keywords: BRT viaducts; CMT; keypoint matching; structural health monitoring; vibration measurement; vision-based sensor.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Vision sensor implementation procedure.
Figure 2
Figure 2
Effects of preprocessing: (a) Original image; (b) Preprocessed image.
Figure 3
Figure 3
Procedure for object region identification in the second frame.
Figure 4
Figure 4
Average number of active keypoints for a sample video with different combinations of detectors and descriptors.
Figure 5
Figure 5
Performance comparison of different combination pairs.
Figure 6
Figure 6
Error analysis of scaling factor: (a) 3D view of image plane and object plane; (b) Optical axis non-perpendicular to object plane in the vertical direction; (c) Horizontal direction.
Figure 7
Figure 7
Error analysis results: (a) Effects of optical axis tilt angle (f = 50); (b) Effects of optical focal length (θ = 10°).
Figure 7
Figure 7
Error analysis results: (a) Effects of optical axis tilt angle (f = 50); (b) Effects of optical focal length (θ = 10°).
Figure 8
Figure 8
Error analysis results when the measurement point gets closer to the known dimension: (a) Effects of optical axis tilt angle (f = 50); (b) Effects of optical focal length (θ = 10°).
Figure 9
Figure 9
Setup for moving platform experiment: (a) Experimental setup; (b) Setup of target plant region.
Figure 10
Figure 10
Target plate: (a) Artificial target; (b) Free targets.
Figure 11
Figure 11
Artificial measurement comparisons: (a) Measurement results of vision-sensor compared with standard values; (b) Measurement results of STDS compared with standard values. (f = 0.05 Hz, A = 9 mm).
Figure 12
Figure 12
Exceptional artificial measurement results: (a) Ι-2; (b) Ι-4.
Figure 13
Figure 13
Free target measurement comparisons: (a) Measurement results of vision sensor capturing target one compared with standard values; (b) Measurement results of vision sensor capturing target two compared with standard values; (c) Measurement results of STDS compared with standard values. (f = 0.1 Hz, A = 9 mm).
Figure 13
Figure 13
Free target measurement comparisons: (a) Measurement results of vision sensor capturing target one compared with standard values; (b) Measurement results of vision sensor capturing target two compared with standard values; (c) Measurement results of STDS compared with standard values. (f = 0.1 Hz, A = 9 mm).
Figure 14
Figure 14
Free target measurement results of vision sensor capturing (a) Target one; (b) Target two. (f = 1.0 Hz, A = 9 mm)
Figure 15
Figure 15
Setup for shaking table experiment: (a) Video acquisition system; (b) Vibration control system; (c) Target system; (d) Strain acquisition system.
Figure 16
Figure 16
Shaking table test results: (a) Measurement results of vision-sensor compared with standard values; (b) Measurement results of STDS compared with standard values. (f = 15 Hz, A = 3 mm).
Figure 17
Figure 17
Measuring distance test results: (a) Measurement results of vision-sensor compared with standard values; (b) Measurement results of STDS compared with standard values. (D = 5.0 m).
Figure 18
Figure 18
Field test: (a) Experiment environment; (b) Natural target; (c) Displacement by the STDS sensor.
Figure 19
Figure 19
Original vertical displacement from the vision sensor.
Figure 20
Figure 20
Free excitation of bridge: (a) Displacement measurement from the vision sensor and the STDS sensor; (b) and (c) the corresponding Fourier spectrum results.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Alamdari M.M., Rakotoarivelo T., Khoa N.L.D. A spectral-based clustering for structural health monitoring of the Sydney Harbour Bridge. Mech. Syst. Signal Proc. 2017;87:384–400. doi: 10.1016/j.ymssp.2016.10.033. - DOI
    1. Lin T.-K., Chang Y.-S. Development of a real-time scour monitoring system for bridge safety evaluation. Mech. Syst. Signal Proc. 2017;82:503–518. doi: 10.1016/j.ymssp.2016.05.040. - DOI
    1. Sun L.-M., He X.-W., Hayashikawa T., Xie W.-P. Characteristic analysis on train-induced vibration responses of rigid-frame RC viaducts. Struct. Eng. Mech. 2015;55:1015–1035. doi: 10.12989/sem.2015.55.5.1015. - DOI
    1. Feng D.M., Feng M.Q. Experimental validation of cost-effective vision-based structural health monitoring. Mech. Syst. Signal Proc. 2017;88:199–211. doi: 10.1016/j.ymssp.2016.11.021. - DOI
    1. Zhang W.-W., Li J., Hao H., Ma H.-W. Damage detection in bridge structures under moving loads with phase trajectory change of multi-type vibration measurements. Mech. Syst. Signal Proc. 2017;87:410–425. doi: 10.1016/j.ymssp.2016.10.035. - DOI