Timber is susceptible to environmental humidity variations, inevitably resulting in cracks parallel to the wood grain during the service life. Cracks significantly degrade the effective cross-sectional area and seriously affect structural safety and durability. Therefore, it is significant to identify the timber elements’ cracking conditions for providing reliable maintenance. Existing timber structure crack inspection mainly relies on manual work. However, with the rapid development of high-rise and large-span glued timber structure, manual-based crack inspection is not applicable to such structures for increasing workload and uncontactable high-altitude timber elements. In order to make up for the deficiencies of the existing crack detection algorithms, this paper proposed an innovative computer vision-based method inspecting full-scale timber column cracks. In step one, the crack images were stitched to exhibit the full-scale cracking condition. In step two, the YOLOv5 model was trained utilizing 425 images collected from cracked timber structures and performed K-fold crossover validation algorithm. In step three, cracking regions are quantified at the physical level. Field tests showed that the proposed method has a crack identification precision better than 0.2 mm and error below 5% compared with manual measurement, which can provide high-precision, time-saving, and noncontact in-situ crack inspection for timber structures.
WangZXieWWangZ, et al. Strain method for synchronous dynamic measurement of elastic, shear modulus and Poisson’s ratio of wood and wood composites. Constr Build Mater2018; 182: 608–619.
2.
CabaleiroMLindenberghRGardWF, et al. Algorithm for automatic detection and analysis of cracks in timber beams from LiDAR data. Constr Build Mater2017; 130: 41–53.
3.
FrankeSFrankeBHarteAM. Failure modes and reinforcement techniques for timber beams – state of the art. Constr Build Mater2015; 97: 2–13.
4.
ZhangWSongXGuX, et al. Compressive behavior of longitudinally cracked timber columns retrofitted using FRP sheets. J Struct Eng2012; 138(1): 90–98.
5.
MaJYanWLiuG, et al. Complex texture contour feature extraction of cracks in timber structures of ancient architecture based on YOLO algorithm. Adv Civ Eng2022; 2022: 1–13.
6.
HsiehYTsaiYCJ. Machine learning for crack detection: review and model performance comparison. J Comput Civil Eng2020; 34(5): 04020038.
7.
LiBWangKCPZhangA, et al. Automatic classification of pavement crack using deep convolutional neural network. Int J Pavement Eng2020; 21(4): 457–463.
8.
LiSZhaoX. Convolutional neural networks-based crack detection for real concrete surface. In: Conference on sensors and smart structures technologies for civil, mechanical, and aerospace systems denver, SPIE, 2018, p. 105983V.
9.
XuJYuanCGuJ, et al. Innovative synthetic data augmentation for dam crack detection, segmentation, and quantification. Struct Health Monit2023; 22: 2402–2426.
10.
GirshickR. Fast R-CNN. In: IEEE international conference on computer vision, 2015.
11.
QiYLiPXiongB, et al. A two-step computer vision-based framework for bolt loosening detection and its implementation on a smartphone application. Struct Health Monit2022; 21(5): 2048–2062.
12.
YanKZhangZ. Automated asphalt highway pavement crack detection based on deformable single shot multi-box detector under a complex environment. IEEE Access2021; 9: 150925–150938.
13.
JiangYPangDLiC, A deep learning approach for fast detection and classification of concrete damage. Autom Constr2021; 128: 103785.
14.
RamalingamBHayatAAElaraMR, et al. Deep learning based pavement inspection using self-reconfigurable robot. Sensors2021; 21(8): 2595.
15.
ChaiyasarnKBuatikAMohamadH, et al. Integrated pixel–level CNN-FCN crack detection via photogrammetric 3D texture mapping of concrete structures. Autom Constr2022; 140: 104388.
16.
LiuZCaoYWangY, et al. Computer vision–based concrete crack detection using U-net fully convolutional networks, Autom Constr2019; 104: 129–139.
17.
MafiMIzquierdoWCabrerizoM, et al. Survey on mixed impulse and Gaussian denoising filters. IET Image Process2020; 14(16): 4027–4038.
18.
Shreyamsha KumarBK. Image fusion based on pixel significance using cross bilateral filter. Signal, Image Video Process2015; 9(5): 1193–1204.
19.
ZhangXLiuTLiuC, et al. Research on skid resistance of asphalt pavement based on three-dimensional laser-scanning technology and pressure-sensitive film. Constr Build Mater2014; 69: 49–59.
ChenCSeoHJunC, et al. A potential crack region method to detect crack using image processing of multiple thresholding. Signal Image Video Process2022; 16(6): 1673–1681.
22.
FanXWuJShiP, et al. A novel automatic dam crack detection algorithm based on local-global clustering. Multimed Tools Appl2018; 77(20): 26581–26599.
23.
OtsuN. A Threshold selection method from gray-level histograms. Automatica1975; 11(23): 285–296.
24.
SimKSKhoYYTsoCP. Application of contrast enhancement bilateral closing Tophat Otsu thresholding technique on crack images. In: 7th IEEE international conference on cybernetic intelligent systems, London, England, 2008.
25.
QuanYSunJZhangY, et al. The method of the road surface crack detection by the improved otsu threshold. In: IEEE International conference on mechatronics and automation, 2019.
26.
Nhat-DucHNguyenQTranV. Automatic recognition of asphalt pavement cracks using metaheuristic optimized edge detection algorithms and convolution neural network. Autom Constr2018; 94: 203–213.
27.
Ayenu-PrahAAttoh-OkineN. Evaluating pavement cracks with bidimensional empirical mode decomposition. EURASIP J Adv Signal Proces2008; 2008: 861701.
28.
WangZYangZ. Review on image-stitching techniques. Multimedia Syst2020; 26(4): 413–430.
29.
ZhangWLiXYuJ, et al. Remote sensing image mosaic technology based on SURF algorithm in agriculture. EURASIP J Image Vide2018; 2018: 85.
30.
PenlandLBrooksBOchoaE. Long-term methods for high-definition image maps of benthic surveys. Mar Technol Soc J2013; 43(6): 7–15.
31.
WangLSpencerJLiJ, et al. A fast image-stitching algorithm for characterization of cracks in large-scale structures. Smart Struct Syst2021; 27(4); 593–605.
32.
LoweDG. Distinctive image features from scale-invariant keypoints. Int J Comput Vision2004; 60(2): 91–110.
33.
BayHEssATuytelaarsT, et al. Speeded-up robust features (SURF). Comput Vis Image Und2008; 110(3): 346–359.
34.
RubleeERabaudVKonoligeK, et al. ORB: an efficient alternative to SIFT or SURF. In: IEEE 13th International conference on computer vision, 2011, pp. 2564–2571. IEEE.
35.
GhanemSKanungoPPandaG, et al. An improved and low-complexity neural network model for curved lane detection of autonomous driving system. Soft Comput2023; 27(1): 493–504.
36.
MokhnacheAZietL. Cryptanalysis of a pixel permutation based image encryption technique using chaotic map. Trait Signal2020; 37(1): 95–100.
37.
ZhouZWangBLiS, et al. Perceptual fusion of infrared and visible images through a hybrid multi-scale decomposition with Gaussian and bilateral filters. Inform Fusion2016; 30: 15–26.
38.
VivoneGDalla MuraMGarzelliA, et al. A new benchmark based on recent advances in multispectral pansharpening: revisiting pansharpening with classical and emerging pansharpening methods. IEEE Geosci Remote Sens Mag2021; 9(1): 53–81.
WonJParkJShimC, et al. Bridge-surface panoramic-image generation for automated bridge-inspection using deepmatching. Struct Health Monit2020; 20(4): 1689–1703.
41.
XiangdanHYongfengDHaijiaoG, et al. The method of pavement image splicing based on SIFT algorithm. In: WRI global congress on intelligent systems, Xiamen, China, 2009, pp. 538–542. IEEE.
42.
HuangYZhuoZXiaolongX. Image stitching algorithm based on region division for underwater dam crack image. In: IEEE International conference on progress in informatics and computing, 2021.
43.
ChenKQiuHSunM, et al. Experimental and numerical study of moisture distribution and shrinkage crack propagation in cross section of timber members. Constr Build Mater2019; 221: 219–231.
44.
ZhangZ. Flexible camera calibration by viewing a plane from unknown orientations. In: The Proceedings of the Seventh IEEE international conference, Los Alamitos CA, 1999, pp. 666–673. IEEE.
45.
HanSJiangXWuZ. An improved YOLOv5 algorithm for wood defect detection based on attention. IEEE Access2023; 11: 71800–71810.
46.
WangWYuanY. SGN-YOLO: detecting wood defects with improved YOLOv5 based on semi-global network. Sensors2023; 23(21): 8705.
47.
MaXHuHWuP. A No-reference edge-preservation assessment index for SAR image filters under a Bayesian framework based on the ratio gradient. Remote Sens Basel2022; 14(4): 256.
48.
SoniVBhandariAKumarA. Improved sub-band adaptive thresholding function for denoising of satellite image based on evolutionary algorithms. IET Signal Process2013; 7(8): 720–730.
49.
Technical standard for maintenance and strengthening of historic timber building. In: GB/T 50165-2020, China Building Industry Press, Beijing, 2020.
50.
ChoiDBellWKimD, et al. UAV-driven structural crack detection and location determination using convolutional neural networks. Sensors2021; 21(8): 2650.
51.
LeiBRenYWangN, et al. Design of a new low–cost unmanned aerial vehicle and vision-based concrete crack inspection method. Struct Health Monit2020; 19(6): 1871–1883.
52.
NaYChongZTianhaoL. Design of crack monitoring system for Chinese ancient wooden building based on UAV and CV. Eng Mech2021; 38(03): 27–39.
53.
KongQGuJXiongB, et al. Vision-aided three-dimensional damage quantification and finite element model geometric updating for reinforced concrete structures. Comput Aided Civ Inf2023; 38(17): 2378–2390.
