This article presents a computer vision damage assessment approach that relates surface crack patterns to damage levels and stress state characteristics in conventionally reinforced concrete and steel fiber–reinforced concrete panels. Previous studies have focused on crack patterns for specific structural element types such as beams and columns, but this study considers stress states in a more general framework. In particular, image data from previously published panel test specimens subjected to nominally constant stress have been collected to develop image-based estimation models capable of quantifying damage levels and stress components for full-panel crack patterns, and to investigate subimage sampling strategies to approximate full-panel results using partial-panel images. The objective here is to show that the analog of representative volume elements can be extended to image-based analysis contexts. The image datasets used in this article have been obtained from five different published studies, which provided 189 crack pattern images captured from concrete and steel fiber–reinforced concrete shear panel specimens. Given the limited size of the dataset, a feature-based computer vision approach has been used, with various geometric attributes of surface crack patterns used to train the estimation models. Within the limits of the data available, the preliminary results presented here indicate that quantifiable correlations exist such that stress state and damage level estimation models are valid across a range of loadings (i.e. reverse cyclic and monotonic) and materials (reinforced concrete and steel fiber–reinforced concrete), and that with appropriate sampling techniques, it is possible for subsampled images to yield estimations similar to full-panel results. These localized correlations between crack patterns and stress states potentially could be used in broader contexts for damage assessment of more general reinforced concrete and steel fiber–reinforced concrete members.
CalviPMProestosGTRuggieroDM. Towards the development of direct crack-based assessment of structures. ACI Struct J2018; 328: 9.1–9.20.
2.
ZhuZGermanSBrilakisI. Visual retrieval of concrete crack properties for automated post-earthquake structural safety evaluation. Automat Constr2011; 20(7): 874–883.
3.
FarhidzadehADehghan-NiriEMoustafaA, et al. Damage assessment of reinforced concrete structures using fractal analysis of residual crack patterns. Exp Mech2013; 53(9): 1607–1619.
YamaguchiTHashimotoS. Fast crack detection method for large-size concrete surface images using percolation-based image processing. Mach Vision Appl2010; 21(5): 797–809.
7.
DestrebecqJFToussaintEFerrierE. Analysis of cracks and deformations in a full scale reinforced concrete beam using a digital image correlation technique. Exp Mech2011; 51(6): 879–890.
8.
ZhuZBrilakisIParra-MontesinosG. Real-time concrete damage visual assessment for first responders. In: Proceedings of the American Society of Civil Engineers (ASCE) construction research congress, Seattle, WA, 5–7 April 2009, pp. 1204–1213. Reston, VA: ASCE.
9.
LattanziDMillerGREberhardMO, et al. Bridge column maximum drift estimation via computer vision. J Comput Civil Eng2015; 30(4): 04015051.
10.
DavoudiRMillerGRKutzJN. Structural load estimation using machine vision and surface crack patterns for shear-critical RC beams and slabs. J Comput Civil Eng2018; 32(4): 04018024.
11.
DavoudiRMillerGRKutzJN. Data-driven vision-based inspection for reinforced concrete beams and slabs: quantitative damage and load estimation. Automat Constr2018; 96: 292–309.
JahanshahiMRKellyJSMasriSF, et al. A survey and evaluation of promising approaches for automatic image-based defect detection of bridge structures. Struct Infrastruct E2009; 5: 455–486.
14.
KochCGeorgievaKKasireddyV, et al. A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure. Adv Eng Inform2015; 29(2): 196–210 (Special issue: infrastructure computer vision).
15.
ItoAAokiYHashimotoS. Accurate extraction and measurement of fine cracks from concrete block surface image. In: Proceedings of the Institute of Electrical and Electronics Engineers (IEEE) 2002 28th annual conference of the industrial electronics society (IECON’02), Seville, 5–8 November 2002, vol. 3, pp. 2202–2207. New York: IEEE.
16.
EbrahimkhanlouAFarhidzadehASalamoneS. Multifractal analysis of crack patterns in reinforced concrete shear walls. Struct Health Monit2016; 15(1): 81–92.
17.
EbrahimkhanlouASalamoneS. A probabilistic model for visual inspection of concrete shear walls. In: Proceedings of the SPIE 10168, sensors and smart structures technologies for civil, mechanical, and aerospace systems (ed LynchJP), Portland, OR, 25–29 March 2017, vol. 10168. Bellingham, WA: SPIE.
18.
GermanSBrilakisIDesRochesR. Comprehensive property retrieval and measurement of concrete spalling using machine vision for post-earthquake safety assessments. In: Proceedings of the SPIE 8345, sensors and smart structures technologies for civil, mechanical, and aerospace systems, San Diego, CA, 11–15 March 2012, vol. 8345, p. 83454S. Bellingham, WA: SPIE.
19.
ChaYJChoiWBüyüköztürkO. Deep learning-based crack damage detection using convolutional neural networks. Comput-Aided Civ Inf2017; 32(5): 361–378.
20.
FengCLiuMYKaoCC, et al. Deep active learning for civil infrastructure defect detection and classification. Cambridge, MA: Mitsubishi Electric Research Laboratories, Inc., 2017.
21.
AlipourMHarrisDKMillerGR. Robust pixel-level crack detection using deep fully convolutional neural networks. J Comput Civil Eng2019; 33(6): 04019040.
22.
ChenFCJahanshahiMR. NB-CNN: deep learning-based crack detection using convolutional neural network and naive bayes data fusion. IEEE T Ind Electron2018; 65(5): 4392–4400.
23.
EbrahimkhanlouADubucBSalamoneS. A generalizable deep learning framework for localizing and characterizing acoustic emission sources in riveted metallic panels. Mech Syst Signal Pr2019; 130: 248–272.
24.
GaoYMosalamKM. Deep transfer learning for image-based structural damage recognition. Comput-Aided Civ Inf2018; 33(9): 748–768.
25.
GuoTWuLWangC, et al. Damage detection in a novel deep-learning framework: a robust method for feature extraction. Struct Health Monit. Epub ahead of print 27May2019. DOI: 10.1177/1475921719846051.
26.
AthaDJJahanshahiMR. Evaluation of deep learning approaches based on convolutional neural networks for corrosion detection. Struct Health Monit2018; 17(5): 1110–1128.
27.
BaşyiğitCÇomakBKılınçarslanŞ, et al. Assessment of concrete compressive strength by image processing technique. Constr Build Mater2012; 37: 526–532 (Special issue: non destructive techniques for assessment of concrete).
28.
ZhangLYueXWangL, et al. Estimating cement compressive strength from microstructural images using GEP with probabilistic polarized similarity weight tournament selection. In: Proceedings of the genetic and evolutionary computation conference (GECCO’18), Kyoto, Japan, 15–19 July 2018, pp. 1403–1410. New York: ACM.
29.
JangYAhnYHKimHY. Estimating compressive strength of concrete using deep convolutional neural networks with digital microscope images. J Comput Civil Eng2019; 33: 04019018.
30.
VecchioFJ. Shear rig design. PhD Thesis, University of Toronto, Toronto, ON, Canada, 1979.
31.
VecchioFJCollinsMP. The modified compression-field theory for reinforced concrete elements subjected to shear. ACI J1986; 83(2): 219–231.
32.
VecchioFJ. Disturbed stress field model for reinforced concrete: formulation. J Struct Eng: ASCE2000; 126(9): 1070–1077.
33.
VecchioFJ. Disturbed stress field model for reinforced concrete: implementation. J Struct Eng: ASCE2001; 127(1): 12–20.
34.
BentzECCollinsMP. Development of the 2004 Canadian Standards Association (CSA) A23.3 shear provisions for reinforced concrete. Can J Civil Eng2006; 33(5): 521–534.
35.
American Association of State Highway and Transportation Officials (AASHTO). AASHTO LRFD bridge design specifications. Washington, DC: AASHTO, Inc., 2007.
36.
TaerweLMatthysS; fib Special Activity Group NMC. fib model code for concrete structures 2010. Lausanne: Ernst & Sohn, Wiley, 2013.
37.
CalviPMBentzECCollinsMP. Model for assessment of cracked reinforced concrete membrane elements subjected to shear and axial loads. ACI Struct J2018; 115(2): 501–509.
38.
CalviPMBentzECCollinsMP. Pure mechanics crack model for shear stress transfer in cracked reinforced concrete. ACI Struct J2017; 114: 545–554.
39.
XieL. The influence of axial load and prestress on the shear strength of web-shear critical reinforced concrete elements. PhD Thesis, University of Toronto, Toronto, ON, Canada, 2009.
40.
RuggieroDMV. The behaviour of reinforced concrete subjected to reversed cyclic shear. PhD Thesis, University of Toronto, Toronto, ON, Canada, 2015.
41.
CarnovaleDJ. Behaviour and analysis of steel and macro-synthetic fibre reinforced concrete subjected to reversed cyclic loading: a pilot investigation. PhD Thesis, University of Toronto, Toronto, ON, Canada, 2013.
42.
SusetyoJ. Fibre reinforcement for shrinkage crack control in prestressed, precast segmental bridges. PhD Thesis, University of Toronto, Toronto, ON, Canada, 2009.
43.
LuoWJW. Behaviour and analysis of steel fibre-reinforced concrete under reversed cyclic loading. PhD Thesis, University of Toronto, Toronto, ON, Canada, 2014.
44.
CannyJ. A computational approach to edge detection. IEEE T Pattern Anal1986; 8(6): 679–698.
