Surface damage is an important indicator for evaluating the safety and durability of bridges. As manual visual inspections are often time-consuming and risky, alternative approaches are essential for effective assessments. Computer vision-based methods have shown the potential for improved inspection utilizing a set of images acquired during a bridge inspection. However, because the position and orientation of a camera are different even for the same damage in routine inspections, tracking the progression of damage over time is challenging in practice. This study presents an integrated framework for the long-term monitoring of structural damage based on multi-view images captured from routine inspections of bridges. In terms of qualitative assessment, a time series of images are grouped for individual damages based on a similarity index. Afterward, a group of pixels for structural damage in each image are mapped onto a common coordinate system, tracking the progression of the same damage over time. In the case of quantitative assessment, a scale conversion factor is calculated using the global navigation satellite system data, in which a plane fitting algorithm is employed to calculate the damage area in physical units. The proposed method is validated using an in-service bridge over a period of 120 days, enabling the long-term assessment of crack, spalling, and water leakage with a maximum error of 4.61%.
FeldJCarperKL. Construction failure. New York: John Wiley & Sons1996.
2.
LiuYWeyersRE. Modeling the time-to-corrosion cracking in chloride contaminated reinforced concrete structures. ACI Mater J1998; 95: 675–680.
3.
HendricksLJBaxterJSChouY, et al. High-speed acoustic impact-echo sounding of concrete bridge decks. J Nondestruct Eval2020; 39: 58.
4.
American Association of State Highway and Transportation Officials. AASHTO bridge element inspection guide manual. Washington, DC: AASHTO, 2010.
5.
AnYChatziESimS-H, et al. Recent progress and future trends on damage identification methods for bridge structures. Struct Control Health Monit2019; 26: e2416.
6.
JangKKimNAnY-K. Deep learning-based autonomous concrete crack evaluation through hybrid image scanning. Struct Health Monit2019; 18: 1722–1737.
7.
JiangYPangDLiC. A deep learning approach for fast detection and classification of concrete damage. Automat Constr2021; 128: 103785.
8.
EllenbergAKontsosAMoonF, et al. Bridge related damage quantification using unmanned aerial vehicle imagery. Struct Control Health Monit2016; 23: 1168–1179.
SonySLaventureSSadhuA. A literature review of next-generation smart sensing technology in structural health monitoring. Struct Control Health Monit2019; 26: e2321.
LiuY-FChoSSpencerBFJr, et al. Concrete crack assessment using digital image processing and 3D scene reconstruction. J Comput Civil Eng2016; 30: 04014124.
13.
KimHAhnEChoS, et al. Comparative analysis of image binarization methods for crack identification in concrete structures. Cem Concr Res2017; 99: 53–61.
14.
ChenJ-HSuM-CCaoR, et al. A self organizing map optimization based image recognition and processing model for bridge crack inspection. Automat Constr2017; 73: 58–66.
15.
SinhaSKFieguthPW. Automated detection of cracks in buried concrete pipe images. Automat Constr2006; 15: 58–72.
16.
JahanshahiMRMasriSF. Adaptive vision-based crack detection using 3D scene reconstruction for condition assessment of structures. Automat Constr2012; 22: 567–576.
ChaY-JChoiWBüyüköztürkO. Deep learning-based crack damage detection using convolutional neural networks. Comput Aided Civ Inf2017; 32: 361–378.
19.
Mohtasham KhaniMVahidniaSGhasemzadehL, et al. Deep-learning-based crack detection with applications for the structural health monitoring of gas turbines. Struct Health Monit2020; 19(5): 1440–1452.
20.
ShiPFanXNiJ, et al. A detection and classification approach for underwater dam cracks. Struct Health Monit2016; 15(5): 541–554.
21.
AnYKongLHouC, et al. An adaptable rotated bounding box method for automatic detection of arbitrary-oriented cracks. Struct Health Monit2024; 23(6): 3312–3335.
22.
WangNZhaoXZhaoP, et al. Automatic damage detection of historic masonry buildings based on mobile deep learning. Automat Constr2019; 103: 53–66.
23.
AgyemangIOZhangXAdjei-MensahI, et al. Automated vision-based structural health inspection and assessment for post-construction civil infrastructure. Automat Constr2023; 156: 105153.
24.
KimBChoS. Automated multiple concrete damage detection using instance segmentation deep learning model. Appl Sci2020; 10: 8008.
25.
ChenKReichardGXuX, et al. Automated crack segmentation in close-range building façade inspection images using deep learning techniques. J Build Eng2021; 43: 102913.
26.
XuYFanYLiH. Lightweight semantic segmentation of complex structural damage recognition for actual bridges. Struct Health Monit2023; 22(5): 3250–3269.
27.
ArafinPBillahAMIssaA. Deep learning-based concrete defects classification and detection using semantic segmentation. Struct Health Monit2024; 23: 383–409.
28.
KatsamenisIDoulamisNDoulamisA, et al. Simultaneous precise localization and classification of metal rust defects for robotic-driven maintenance and prefabrication using residual attention U-Net. Automat Constr2022; 137: 104182.
29.
WangJ-FLiX-XWangY-W, et al. Automatic detection and evaluation of multitype surface defects in metro tunnels based on mobile laser scanning. Struct Health Monit. Epub ahead of print 2025. https://doi.org/10.1177/14759217251344171
30.
WangRShaoYLiQ, et al. A novel transformer-based semantic segmentation framework for structural condition assessment. Struct Health Monit2024; 23(2): 1170–1183.
31.
BaiZLiuTZouD, et al. Image-based reinforced concrete component mechanical damage recognition and structural safety rapid assessment using deep learning with frequency information. Automat Constr2023; 150: 104839.
32.
ZhangCYinZQinR. Attention-enhanced co-interactive fusion network (AECIF-Net) for automated structural condition assessment in visual inspection. Automat Constr2024; 159: 105292.
33.
FengD-CYiXDegerZT, et al. Rapid post-earthquake damage assessment of building portfolios through deep learning-based component-level image recognition. J Build Eng2024; 98: 111380.
34.
ChenSLaeferDFManginaE, et al. UAV bridge inspection through evaluated 3D reconstructions. J Bridge Eng2019; 24: 05019001.
35.
KimHYoonJHongJ, et al. Automated damage localization and quantification in concrete bridges using point cloud-based surface-fitting strategy. J Comput Civil Eng2021; 35: 04021028.
36.
LouYMengSZhouY. Deep learning-based three-dimensional crack damage detection method using point clouds without color information. Struct Health Monit2025; 24(2): 657–675.
37.
FengC-QLiB-LLiuY-F, et al. Crack assessment using multi-sensor fusion simultaneous localization and mapping (SLAM) and image super-resolution for bridge inspection. Automat Constr2023; 155: 105047.
38.
DingWYangHYuK, et al. Crack detection and quantification for concrete structures using UAV and transformer. Automat Constr2023; 152: 104929.
39.
JiangSChengYZhangJ. Vision-guided unmanned aerial system for rapid multiple-type damage detection and localization. Struct Health Monit2023; 22(1): 319–337.
40.
LiuY-FNieXFanJ-S, et al. Image-based crack assessment of bridge piers using unmanned aerial vehicles and three-dimensional scene reconstruction. Comput Aided Civ Inf2020; 35: 511–529.
41.
PerryBJGuoYAtaderoR, et al. Streamlined bridge inspection system utilizing unmanned aerial vehicles (UAVs) and machine learning. Measurement2020; 164: 108048.
42.
KimHSimS-HSpencerBFJr. Automated concrete crack evaluation using stereo vision with two different focal lengths. Automat Constr2022; 135: 104136.
43.
Pantoja-RoseroBGAchantaRBeyerK. Damage-augmented digital twins towards the automated inspection of buildings. Automat Constr2023; 150: 104842.
44.
XiaoJ-LFanJ-SLiuY-F, et al. Region of interest (ROI) extraction and crack detection for UAV-based bridge inspection using point cloud segmentation and 3D-to-2D projection. Automat Constr2024; 158: 105226.
45.
YamaneTChunPJDangJ, et al. Recording of bridge damage areas by 3D integration of multiple images and reduction of the variability in detected results. Comput Aided Civ Inf2023; 38: 2391–2407.
46.
NiYMaoJWangH, et al. Surface damage detection and localization for bridge visual inspection based on deep learning and 3D reconstruction. Struct Control Health Monit2024; 2024: 9988793.
47.
YamaneTChunP-JHondaR. Detecting and localising damage based on image recognition and structure from motion, and reflecting it in a 3D bridge model. Struct Infrastruct Eng2024; 20: 594–606.
48.
KimGChaY. 3D pixelwise damage mapping using a deep attention based modified Nerfacto. Automat Constr2024; 168: 105878.
49.
SarlinP-ECadenaCSiegwartR, et al. From coarse to fine: robust hierarchical localization at large scale. In: IEEE/CVF conference on computer vision and pattern recognition, Long Beach, CA, USA, 15–20 June 2019, pp. 12716–12725. Piscataway, NJ: IEEE.
50.
BianchiELSakibNWoolseyC, et al. Bridge inspection component registration for damage evolution. Struct Health Monit2023; 22: 472–495.
HeKGkioxariGDollárP, et al. Mask R-CNN. In: Proceedings of the IEEE international conference on computer vision, Venice, Italy, 22–29 October 2017, pp. 2961–2969. Piscataway, NJ: IEEE.
53.
RenSHeKGirshickR, et al. Faster R-CNN: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst2015; 28: 2577031.
54.
TervenJCórdova-EsparzaD-MRomero-GonzálezJ-A. A comprehensive review of YOLO architectures in computer vision: from YOLOv1 to YOLOv8 and YOLO-NAS. Mach Learn Knowl Extr2023; 5: 1680–1716.
55.
HartleyRZissermanA. Multiple view geometry in computer vision. Cambridge: Cambridge University Press, 2003.
56.
ArandjelovicRGronatPToriiA, et al. NetVLAD: CNN architecture for weakly supervised place recognition. In: IEEE conference on computer vision pattern recognition, Las Vegas, NV, USA, 27–30 June 2016, pp. 5297–5307. Piscataway, NJ: IEEE.
57.
ToriiAArandjelovicRSivicJ, et al. 24/7 place recognition by view synthesis. IEEE Trans Pattern Anal Mach Intell2018; 40: 257–271.
58.
SarlinP-EDeToneDMalisiewiczT, et al. SuperGlue: learning feature matching with graph neural networks. In: IEEE/CVF conference on computer vision pattern recognition, Seattle, WA, USA, 13–19 June 2020, pp. 4938–4947. Piscataway, NJ: IEEE.
59.
WangKZhaoGWangY, et al. SaliencyVR: saliency matching based visual relocalization for autonomous vehicle. IEEE Trans Intell Veh2025; 10(2): 876–885.
60.
CabreraJJCéspedesOJCebolladaS, et al. An evaluation of CNN models and data augmentation techniques in hierarchical localization of mobile robots. Evol Syst2024; 15: 1991–2003.
61.
SattlerTWeyandTLeibeB, et al. Image retrieval for image-based localization revisited. In: Proceedings of the British machine vision conference (BMVC), Guildford, UK, 3–7 September 2012, p. 4. Guildford: BMVA Press.
62.
MaddernWPascoeGChrisL, et al. 1 year, 1000 km: the Oxford RobotCar dataset. Int J Robot Res2017; 36(1): 3–15.
63.
BansalABadinoHHuberD. Understanding how camera configuration and environmental conditions affect appearance-based localization. In: IEEE intelligent vehicles symposium proceedings, Dearborn, MI, USA, 8–11 June 2014, pp. 800–807. Piscataway, NJ: IEEE.
64.
ZhangCChangC-CJamshidiM. Concrete bridge surface damage detection using a single-stage detector. Comput Aided Civ Inf2020; 35: 389–409.
65.
SavinoPTondoloF. Civil infrastructure defect assessment using pixel-wise segmentation based on deep learning. J Civ Struct Health Monit2023; 13: 35–48.
66.
ChuHDengLYuanH, et al. A transformer and self-cascade operation-based architecture for segmenting high-resolution bridge cracks. Automat Constr2024; 158: 105194.
67.
ZhangW-JWanH-PToddMD. An efficient 2D-3D fusion method for bridge damage detection under complex backgrounds with imbalanced training data. Adv Eng Inform2025; 65: 103373.
68.
NiY-HWangHMaoJ-X, et al. Quantitative detection of typical bridge surface damages based on global attention mechanism and YOLOv7 network. Struct Health Monit2025; 24: 941–962.
69.
ZhouLJiangYJiaH, et al. UAV vision-based crack quantification and visualization of bridges: system design and engineering application. Struct Health Monit2025; 24: 1083–1100.
70.
QiYLinPYangG, et al. Crack detection and 3D visualization of crack distribution for UAV-based bridge inspection using efficient approaches. Structures2025; 78: 109075.
71.
DengLSunTYangL, et al. Binocular video-based 3D reconstruction and length quantification of cracks in concrete structures. Automat Constr2023; 148: 104743.
72.
GeLSadhuA. Deep learning-enhanced smart ground robotic system for automated structural damage inspection and mapping. Automat Constr2025; 170: 105951.
73.
SohnH-GLimY-MYunK-H, et al. Monitoring crack changes in concrete structures. Comput Aided Civ Inf2005; 20(1): 52–61.
74.
BelloniVSjölanderARavanelliR, et al. Crack monitoring from motion (CMfM): crack detection and measurement using cameras with non-fixed positions. Automat Constr2023; 156: 105072.
75.
DrydenILMardiaKV. Statistical shape analysis: with applications in R. New York, NY: John Wiley & Sons, 2016.
76.
SchonbergerJLFrahmJ-M. Structure-from-motion revisited. In: IEEE/CVF conference on computer vision pattern recognition, Las Vegas, NV, USA, 27–30 June 2016, pp. 4104–4113. Piscataway, NJ: IEEE.
77.
DeToneDMalisiewiczTRabinovichA. SuperPoint: self-supervised interest point detection and description. In: IEEE conference on computer vision and pattern recognition workshops, Salt Lake City, UT, USA, 18–22 June 2018, pp. 224–236. Piscataway, NJ: IEEE.
78.
LinT-YMaireMBelongieS, et al. Microsoft COCO: common objects in context. In: European conference on computer vision, Zurich, Switzerland, 6–12 September 2014, pp. 740–755. Cham: Springer.
79.
FlotzingerJRöschPJBramlT. dacl10k: Benchmark for semantic bridge damage segmentation. In: IEEE/CVF winter conference on applications of computer vision, Waikoloa, HI, USA, 3–8 January 2024, pp. 8626–8635. Piscataway, NJ: IEEE.
80.
FujishimaTDangJChunP. Training images for semantic segmentation of bridge damage detection [dataset]. J-Stage Data, 2023.
81.
SohaibMJamilSKimJ-M. An ensemble approach for robust automated crack detection and segmentation in concrete structures. Sensors2024; 24: 257.
82.
YuFYeGJiangQ, et al. Imaging-based instance segmentation of pavement cracks using an improved YOLOv8 network. Struct Control Health Monit2025; 2025(1): 1660649.
83.
KirillovAMintunERaviN, et al. Segment anything. In: IEEE/CVF international conference on computer vision, Paris, France, 1–6 October 2023, pp. 4015–4026. Piscataway, NJ: IEEE.
84.
WanQHuangZLuJ, et al. Seaformer: squeeze-enhanced axial transformer for mobile semantic segmentation. In: The 11th international conference on learning representations, Kigali, Rwanda, 1–5 May 2023.
85.
GuJKwonHWangD, et al. Multi-scale high-resolution vision transformer for semantic segmentation. In: IEEE/CVF conference on computer vision and pattern recognition, New Orleans, LA, USA, 18–24 June 2022, pp. 12094–12103. Piscataway, NJ: IEEE.
