Rapid and accurate damage assessment of railway viaducts is critical following an earthquake. This study proposes a novel two-phase framework for comprehensive damage assessment for post-earthquake reinforced concrete components in railway viaducts, which integrates image classification and instance segmentation. High-resolution images captured by cameras are first cropped or resized into standardized image blocks. In the first phase, a classification model categorizes these image blocks into background, concrete crack, and exposed rebar, enabling preliminary damage assessment of the concrete components. In the second phase, instance segmentation is applied only to the image blocks identified as containing concrete crack or exposed rebar to precisely locate the damage and achieve detailed assessment. By employing image classification to exclude non-damaged areas, the method significantly reduces the computational cost while maintaining high accuracy. The proposed method is validated using the Tokaido dataset of post-earthquake railway viaducts, demonstrating superior performance in both detection accuracy and processing efficiency compared to conventional methods.
AliMLZhangZ (2024) The YOLO framework: a comprehensive review of evolution, applications, and benchmarks in object detection. Computers13(12): 336.
2.
AlipourMHarrisDK (2020) Increasing the robustness of material-specific deep learning models for crack detection across different materials. Engineering Structures206: 110157.
3.
ChaY-JChoiWBüyüköztürkO (2017) Deep learning‐based crack damage detection using convolutional neural networks. Computer-Aided Civil and Infrastructure Engineering32(5): 361–378.
4.
ChaY-JChoiWSuhG, et al. (2018) Autonomous structural visual inspection using region‐based deep learning for detecting multiple damage types. Computer-Aided Civil and Infrastructure Engineering33(9): 731–747.
5.
ChangXZhangYHanC, et al. (2026) Structural evaluation of cracked shield tunnels using computer-vision-based model updating techniques. Advanced Engineering Informatics69: 103818.
6.
ChenL-kJiangL-zQinH-x, et al. (2019) Nonlinear seismic assessment of isolated high-speed railway bridge subjected to near-fault earthquake scenarios. Structure and Infrastructure Engineering15(11): 1529–1547.
7.
ChenZ-WRuanX-ZLiuK-M, et al. (2022) Fully automated natural frequency identification based on deep-learning-enhanced computer vision and power spectral density transmissibility. Advances in Structural Engineering25(13): 2722–2737.
8.
ChenLChenWWangL, et al. (2023) Convolutional neural networks (CNNs)-based multi-category damage detection and recognition of high-speed rail (HSR) reinforced concrete (RC) bridges using test images. Engineering Structures276: 115306.
9.
ChengM-YSholehMNHarsonoK (2024) Automated vision-based post-earthquake safety assessment for bridges using STF-PointRend and EfficientNetB0. Structural Health Monitoring23(2): 776–795.
10.
FujinoYPachecoBMNakamuraS-I, et al. (1993) Synchronization of human walking observed during lateral vibration of a congested pedestrian bridge. Earthquake Engineering & Structural Dynamics22(9): 741–758.
11.
GerumPCLAltayABaykal-GürsoyM (2019) Data-driven predictive maintenance scheduling policies for railways. Transportation Research Part C: Emerging Technologies107: 137–154.
12.
GuoJMaoRMaK, et al. (2025) Deep learning-based approach for identifying vortex-induced vibrations in stay cables. Advances in Structural Engineering28(4): 690–715.
13.
HurtadoACAlamdariMMAtroshchenkoE, et al. (2024) A data-driven methodology for bridge indirect health monitoring using unsupervised computer vision. Mechanical Systems and Signal Processing210: 111109.
14.
JinZFuYSunZ (2025) Time–frequency balanced data reconstruction for SHM based on wavelet-enhanced multi-scale residual convolutional block and frequency distribution loss. Mechanical Systems and Signal Processing237: 113127.
15.
LeiXSiringoringoDMSunZ, et al. (2023) Displacement response estimation of a cable-stayed bridge subjected to various loading conditions with one-dimensional residual convolutional autoencoder method. Structural Health Monitoring22(3): 1790–1806.
16.
LevineNMNarazakiYBillieF, et al. (2022) Performance-based post-earthquake building evaluations using computer vision-derived damage observations. Advances in Structural Engineering25(16): 3425–3449.
17.
LiuRZengW (2025) Automatic detection of structural defects in tunnel lining via network pruning and knowledge distillation in YOLO. Structural Health Monitoring. doi: 10.1177/1475921724128906.
18.
LuoLSunLSongM, et al. (2025) Joint load-parameter-response identification using a physics-encoded neural network. Mechanical Systems and Signal Processing230: 112597.
19.
MaddalenaETLianYJonesCN (2020) Data-driven methods for building control—A review and promising future directions. Control Engineering Practice95: 104211.
20.
MontenegroPACalçada NVPRTanabeM, et al. (2016) Running safety assessment of trains moving over bridges subjected to moderate earthquakes. Earthquake Engineering & Structural Dynamics45(3): 483–504.
21.
MoslehAMeixedoARibeiroD, et al. (2023a) Early wheel flat detection: an automatic data-driven wavelet-based approach for railways. Vehicle System Dynamics61(6): 1644–1673.
22.
MoslehAMeixedoARibeiroD, et al. (2023b) Machine learning approach for wheel flat detection of railway train wheels. Transportation Research Procedia72: 4199–4206.
23.
NarazakiYHoskereVYoshidaK, et al. (2021) Synthetic environments for vision-based structural condition assessment of Japanese high-speed railway viaducts. Mechanical Systems and Signal Processing160: 107850.
24.
NayyeriFHouLZhouJ, et al. (2019) Foreground–background separation technique for crack detection. Computer-Aided Civil and Infrastructure Engineering34(6): 457–470.
25.
OzakgulKYilmazMFYilmazF, et al. (2024) Serviceability fragility assessment of non-seismically designed railway viaducts in Turkey under near-field and far-field earthquakes. Structures68: 107102.
26.
PanXYangTY (2020) Postdisaster image‐based damage detection and repair cost estimation of reinforced concrete buildings using dual convolutional neural networks. Computer-Aided Civil and Infrastructure Engineering35(5): 495–510.
27.
RedmonJDivvalaSGirshickR, et al. (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. Las Vegas, NV, USA, 27 to 30 June 2016, 779–788.
28.
ShuJYangHLiuG, et al. (2025) Post-earthquake inspection of high-speed railway viaducts with multi-scale task interaction deep learning strategy. Advances in Structural Engineering28: 1–16.
29.
SiringoringoDMFujinoY (2018) Seismic response of a suspension bridge: insights from long‐term full‐scale seismic monitoring system. Structural Control and Health Monitoring25(11): e2252.
30.
SpencerBFJrHoskereVNarazakiY (2019) Advances in computer vision-based civil infrastructure inspection and monitoring. Engineering5(2): 199–222.
31.
SunZSantosJCaetanoE (2022) Vision and support vector machine–based train classification using weigh-in-motion data. Journal of Bridge Engineering27(6): 06022001.
32.
SunZCaetanoEPereiraS, et al. (2023a) Employing histogram of oriented gradient to enhance concrete crack detection performance with classification algorithm and Bayesian optimization. Engineering Failure Analysis150: 107351.
33.
SunZSunMSiringoringoDM, et al. (2023b) Predicting bridge longitudinal displacement from monitored operational loads with hierarchical CNN for condition assessment. Mechanical Systems and Signal Processing200: 110623.
VodrahalliKBhowmikAK (2017) 3D computer vision based on machine learning with deep neural networks: a review. Journal of the Society for Information Display25(11): 676–694.
36.
WanH-PNiY-Q (2019) Bayesian multi-task learning methodology for reconstruction of structural health monitoring data. Structural Health Monitoring18(4): 1282–1309.
37.
WanH-PZhuY-KLuoY, et al. (2025) Unsupervised deep learning approach for structural anomaly detection using probabilistic features. Structural Health Monitoring24(1): 3–33.
38.
WangXLiLTianW, et al. (2022) Unsupervised one-class classification for condition assessment of bridge cables using Bayesian factor analysis. Smart Structures and Systems29(1): 41–51.
39.
WangJLeiYYangX, et al. (2023) A refinement network embedded with attention mechanism for computer vision based post-earthquake inspections of railway viaduct. Engineering Structures279: 115572.
40.
WeiBWangW-HWangP, et al. (2022) Seismic responses of a high-speed railway (HSR) bridge and track simulation under longitudinal earthquakes. Journal of Earthquake Engineering26(9): 4449–4470.
41.
XieXCaiJWangH, et al. (2022) Sparse‐sensing and superpixel‐based segmentation model for concrete cracks. Computer-Aided Civil and Infrastructure Engineering37(13): 1769–1784.
42.
XiongQKongQXiongH, et al. (2024) Zero-shot knowledge transfer for seismic damage diagnosis through multi-channel 1D CNN integrated with autoencoder-based domain adaptation. Mechanical Systems and Signal Processing217: 111535.
43.
XuYBaoYChenJ, et al. (2019) Surface fatigue crack identification in steel box girder of bridges by a deep fusion convolutional neural network based on consumer-grade camera images. Structural Health Monitoring18(3): 653–674.
44.
YangQYuXFuY (2025) Attention-based encoder for online data anomaly classification in multivariate time series. Journal of Computing in Civil Engineering39(6): 04025094.
45.
YinJRenXLiuR, et al. (2022) Quantitative analysis for resilience-based urban rail systems: a hybrid knowledge-based and data-driven approach. Reliability Engineering & System Safety219: 108183.
46.
ZhangXXieXZhaoH, et al. (2025a) Seismic response prediction method of train-bridge coupled system based on convolutional neural network-bidirectional long short-term memory-attention modeling. Advances in Structural Engineering28(2): 341–357.
47.
ZhangZFuYSunZ (2025b) Advancements in digital twin-enhanced health monitoring and condition assessment of cable-supported bridges. Structures79: 109448.
48.
ZhengZWangPLiuW, et al. (2020) Distance-IoU loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI conference on artificial intelligence, February 7-12, New York.12993–13000.
49.
ZouQZhangZLiQ, et al. (2019) Deepcrack: learning hierarchical convolutional features for crack detection. IEEE Transactions on Image Processing28(3): 1498–1512.
