Fatigue cracks caused by repetitive loads are one of the major threats to the structural integrity of civil infrastructure. Human inspection is the most common method for detecting fatigue cracks, but it is time-consuming, labor-intensive, and unreliable. In this paper, we propose a new vision-based fatigue crack detection and localization method that can detect the fatigue crack with marker-free and high precision using a consumer-grade digital camera. A motion tracking technology called optical flow algorithm is applied to the video for tracking the surface motion of the monitored structure under repetitive load. Then, a crack detection and localization algorithm based on optical flow information entropy are developed to search differential features at different video frames caused by the crack opening and closing. The proposed method’s precision is first validated by doing two experiments and then comparing its precision and efficiency to the existing crack detection methods, including image processing and digital image correlation. The results show that, when compared to the existing vision-based methods, the proposed method can accurately and efficiently identify the fatigue crack even when the crack is surrounded by other crack-like edges, covered by complex surface textures, or invisible to human eyes. In addition, based on the proposed methods, a practical application for calculating the stress intensity factor is given to track crack development.
HouRXiaY. Review on the new development of vibration-based damage identification for civil engineering structures: 2010–2019. J Sound Vibration2021; 491(20): 115741. DOI: 10.1016/j.jsv.2020.115741
2.
RaoASNguyenTNPalaniswamiM, et al.Vision-based automated crack detection using convolutional neural networks for condition assessment of infrastructure. Struct Health Monit2020; 20(2): 1–19. DOI: 10.1177/1475921720965445
3.
AgathosKTatsisKEVlachasK, et al.Parametric reduced order models for output-only vibration-based crack detection in shell structures. Mech Syst Signal Process2022; 162(5): 108051. DOI: 10.1016/j.ymssp.2021.108051
4.
Mata-FalcónJHaefligerSLeeM, et al.Combined application of distributed fibre optical and digital image correlation measurements to structural concrete experiments. Eng Structures2020; 225. 111309, DOI: 10.1016/j.engstruct.2020.111309
5.
AvciOAbdeljaberOKiranyazS, et al.A review of vibration-based damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning applications. Mech Syst Signal Process2021; 147. DOI: 10.1016/j.ymssp.2020.107077
6.
DizajiMSAlipourMHarrisDK. Subsurface damage detection and structural health monitoring using digital image correlation and topology optimization. Eng Structures2021; 230. DOI: 10.1016/j.engstruct.2020.111712
7.
MarchewkaAZiolkowskiPAguilar-VidalV. Framework for Structural Health Monitoring of Steel Bridges by Computer Vision. Sensors2020; 20. DOI: 10.3390/s20030700
8.
FangWDingLLovePED, et al.Computer vision applications in construction safety assurance. Automation in Construction2020; 110. 103013, DOI: 10.1016/j.autcon.2019.103013
9.
RoyGPanigrahiBPohitG. Crack identification in beam-type structural elements using a piezoelectric sensor. Nondestructive Test Eval2020: 36, 1–19. DOI: 10.1080/10589759.2020.1843652
10.
TangQDuCWangX, et al.Temperature and crack detection of steel rods using an all-optical photoacoustic ultrasound system. Construction Building Mater2020; 262. DOI: 10.1016/j.conbuildmat.2020.119537
11.
OliveiraMASimas FilhoEFAlbuquerqueMCS, et al.Ultrasound-based identification of damage in wind turbine blades using novelty detection. Ultrasonics2020; 108: 106166. DOI: 10.1016/j.ultras.2020.106166
12.
SpytekJMrowkaJPieczonkaL, et al.Multi-resolution non-contact damage detection in complex-shaped composite laminates using ultrasound. NDT E Int2020; 116: 102366, DOI: 10.1016/j.ndteint.2020.102366
13.
GallucciLMennaCAngrisaniL, et al.An embedded wireless sensor network with wireless power transmission capability for the structural health monitoring of reinforced concrete structures. Sensors2017; 17: 2566. DOI: 10.3390/s17112566
14.
Di MaioDEwinsDJ. Continuous Scan, a method for performing modal testing using meaningful measurement parameters; Part I. Mech Syst Signal Process2011; 25: 3027–3042. DOI: 10.1016/j.ymssp.2011.05.018
15.
FengDFengMQ. Computer vision for SHM of civil infrastructure: From dynamic response measurement to damage detection – A review. Eng Structures2018; 156: 105–117. DOI: 10.1016/j.engstruct.2017.11.018
16.
DongC-ZCatbasFN. A review of computer vision–based structural health monitoring at local and global levels. Struct Health Monit2020; 20(2): 692–743. DOI: 10.1177/1475921720935585
17.
Mohtasham KhaniMVahidniaSGhasemzadehL, et al.Deep-learning-based crack detection with applications for the structural health monitoring of gas turbines. Struct Health Monit2019; 19: 1440–1452, DOI: 10.1177/1475921719883202
Abdel-QaderIAbudayyehOKellyME. Analysis of edge-detection techniques for crack identification in bridges. J Comput Civil Eng2003; 17(4): 255–263. DOI: 10.1061/(ASCE)0887-3801(2003)17:4(255)
20.
AlipourMHarrisDK. Increasing the robustness of material-specific deep learning models for crack detection across different materials. Eng Structures2020; 206. DOI: 10.1016/j.engstruct.2019.110157
21.
ChaY-JChoiWBüyüköztürkO. Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks. Computer-Aided Civil Infrastructure Eng2017; 32: 361–378. DOI: 10.1111/mice.12263
22.
ZhangKChengHDZhangB. Unified approach to pavement crack and sealed crack detection using preclassification based on transfer learning. J Comput Civil Eng2018; 32: 04018001. DOI: 10.1061/(asce)cp.1943-5487.0000736
23.
HuYGuoWZhuW, et al.Local damage detection of membranes based on Bayesian operational modal analysis and three-dimensional digital image correlation. Mech Syst Signal Process2019; 131: 633–648. DOI: 10.1016/j.ymssp.2019.04.051
24.
Dias-da-CostaDValençaJJúlioE, et al.Crack propagation monitoring using an image deformation approach. Struct Control Health Monit2017; 24. e1973. DOI: 10.1002/stc.1973
25.
NgeljaratanLMoustafaMA. Structural health monitoring and seismic response assessment of bridge structures using target-tracking digital image correlation. Eng Structures2020; 213(15): 110551. DOI: 10.1016/j.engstruct.2020.110551
26.
HalloGLacombeCNéauportJ, et al.Detection and tracking of laser damage sites on fused silica components by digital image correlation. Opt Lasers Eng2021; 146: 106674. DOI: 10.1016/j.optlaseng.2021.106674
27.
CawleyPHuttTThompsonD, et al.Fatigue crack detection using digital image correlation. American Institute of Physics. Am Inst Phys2009; 28: 689–696. DOI: 10.1063/1.3114323
28.
YangYDornCManciniT, et al.Reference-free detection of minute, non-visible, damage using full-field, high-resolution mode shapes output-only identified from digital videos of structures. Struct Health Monit2017; 17: 514–531. DOI: 10.1177/1475921717704385
29.
DongC-ZCelikOCatbasFN. Marker-free monitoring of the grandstand structures and modal identification using computer vision methods. Struct Health Monit2018; 18(5–6): 1491–1509. DOI: 10.1177/1475921718806895
30.
BouguetJY. Pyramidal implementation of the Lucas Kanade feature tracker. Opencv Documents2001; 222: 363–381.
31.
BauerNPathiranaPHodgsonP. Robust Optical Flow with Combined Lucas-Kanade/Horn-Schunck and Automatic Neighborhood Selection. In: 2006 International Conference on Information and Automation, Colombo, Sri Lanka, 15–17 December 2006. IEEE.
32.
CunXCunjunWZiliX, et al.Marker-free vision-based method for vibration measurements of RC structure under seismic vibration. Earthquake Eng Struct Dyn2022; 1–22. DOI: 10.1002/eqe.3637
33.
HuaianYXinjiaZLeT, et al.Measuring grinding surface roughness based on singular value entropy of quaternion. Meas Sci Technology2020; 31(11): 115006. DOI: 10.1088/1361-6501/ab9aa9
34.
XuejunXXiaoningZ. Crack detection of reinforced concrete bridge using video image. J Cent South Univ2013; 20: 2605–2613. DOI: 10.1007/s11771-013-1775-5
35.
ShahrokhinasabEHosseinzadehN. Performance of Image-Based Crack Detection Systems in Concrete Structures. J Soft Comput Civil Eng2020; 4(1): 127–139. DOI: 10.22115/SCCE.2020.218984.1174
36.
PanBQianKXieH, et al.Two-dimensional digital image correlation for in-plane displacement and strain measurement: a review. Meas Sci Technology2009; 20: 062001. DOI: 10.1088/0957-0233/20/6/062001
37.
HoaiLGardinC. Analytical calculation of the stress intensity factor in a surface cracked plate submitted to thermal fatigue loading. Eng Fracture Mech2010; 77: 2354–2369. DOI: 10.1016/j.engfracmech.2010.05.012
38.
YoutangLYadongWLongY. Effect of stress ratio on stress intensity factor of type I crack in A7N01 ALUMINUM ALLOy. Key Eng Mater2018; 774: 259–264. DOI: 10.4028/www.scientific.net/KEM.774.259
39.
XianKuiZ. Numerical determination of stress intensity factors using ABAQUS. American Society of Mechanical Engineers. Pressure Vessels and Piping Division2014; 6: 1–8. DOI: 10.1115/PVP2014-28981
