Similar articles

Abstract: Long-span bridges are usually constructed over waterways that involve substantial ship traffic, resulting in a risk of collisions between the bridge girders and over-height ships. The consequences of this can be severe structural damage or even collapse. Accurate measurement of ship dimensions is an effective way to monitor approaching over-height ships and avoid collisions. However, the performance of current techniques for estimating the size of moving objects can be undermined by large sensor-to-object distance, limiting their applicability. In this study, we propose a digital twin-assisted ship size measurement framework that can overcome such limitations through a predictive model and virtual-to-real-world transfer learning. Specifically, a 3D synthetic environment is first established to generate a synthetic dataset, which includes ship images, positions, and dimensions. Then the pixel information and spatial coordinates of ships are adopted as regressors, and ship dimensions are selected as the output variables to pre-train deep learning models using the generated dataset. Coordinate system transformations are applied to address dataset bias between the simulated world and real-world, as well as improve the model’s generalization. The pre-trained models are compared using supervised virtual-to-real-world transfer learning to select the version with optimal real-world performance. The mean absolute percentage error is only 3.74% across varying camera-to-ship distances, which demonstrates that the proposed method is effective for over-limit ship monitoring.

用于桥梁防船撞预警的船舶尺寸数字孪生测量方法

[1]BianXC, JiangHG, ChenYM, 2010. Accumulative deformation in railway track induced by high-speed traffic loading of the trains. Earthquake Engineering and Engineering Vibration, 9(3):319-326.

[2]BianXC, ShiKH, LiW, et al., 2021. Quantification of railway ballast degradation by abrasion testing and computer-aided morphology analysis. Journal of Materials in Civil Engineering, 33(1):04020411.

[3]BynumP, IssaRRA, OlbinaS, 2013. Building information modeling in support of sustainable design and construction. Journal of Construction Engineering and Management, 139(1):24-34.

[4]ChanPW, LeeYF, 2013. Performance of LIDAR- and radar-based turbulence intensity measurement in comparison with anemometer-based turbulence intensity estimation based on aircraft data for a typical case of terrain-induced turbulence in association with a typhoon. Journal of Zhejiang University-SCIENCE A, 14(7):469-481.

[5]ChenYM, KeH, FredlundDG, et al., 2010. Secondary compression of municipal solid wastes and a compression model for predicting settlement of municipal solid waste landfills. Journal of Geotechnical and Geoenvironmental Engineering, 136(5):706-717.

[6]FanW, YuanWC, FanQW, 2008. Calculation method of ship collision force on bridge using artificial neural network. Journal of Zhejiang University-SCIENCE A, 9(5):614-623.

[7]FanW, SunY, YangCC, et al., 2020. Assessing the response and fragility of concrete bridges under multi-hazard effect of vessel impact and corrosion. Engineering Structures, 225:111279.

[8]FascioneJM, CrewsRT, WrobelJS, 2014. Association of footprint measurements with plantar kinetics: a linear regression model. Journal of the American Podiatric Medical Association, 104(2):125-133.

[9]GaidonA, WangQ, CabonY, et al., 2016. VirtualWorlds as proxy for multi-object tracking analysis. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, p.4340-4349.

[10]GajalakshmiK, PalanivelS, NaliniNJ, et al., 2017. Grain size measurement in optical microstructure using support vector regression. Optik, 138:320-327.

[11]GargoumSA, KarstenL, El-BasyounyK, et al., 2018. Automated assessment of vertical clearance on highways scanned using mobile LiDAR technology. Automation in Construction, 95:260-274.

[12]GuoJ, HeJX, 2020. Dynamic response analysis of ship-bridge collisions experiment. Journal of Zhejiang University-SCIENCE A, 21(7):525-534.

[13]GuoY, LiuRW, QuJX, et al., 2023. Asynchronous trajectory matching-based multimodal maritime data fusion for vessel traffic surveillance in inland waterways. IEEE Transactions on Intelligent Transportation Systems, 24(11):12779-12792.

[14]HouCC, WangH, GuanW, et al., 2025. Road pavement performance prediction using a time series long short-term memory (LSTM) model. Journal of Zhejiang University-SCIENCE A, 26(5):424-437.

[15]HuangQL, WangJZ, SongYX, et al., 2024. Synthetic‐to‐realistic domain adaptation for cold‐start of rail inspection systems. Computer‐Aided Civil and Infrastructure Engineering, 39(3):424-437.

[16]IbrahimA, ArtamaWT, BudisatriaIGS, et al., 2021. Regression model analysis for prediction of body weight from body measurements in female Batur sheep of Banjarnegara District, Indonesia. Biodiversitas Journal of Biological Diversity, 22(7):2723-2730.

[17]InazuD, WasedaT, HibiyaT, et al., 2016. Assessment of GNSS-based height data of multiple ships for measuring and forecasting great tsunamis. Geoscience Letters, 3(1):25.

[18]IuzzolinoML, WalkerME, SzafirD, 2018. Virtual-to-real-world transfer learning for robots on wilderness trails. IEEE/RSJ International Conference on Intelligent Robots and Systems, p.576-582.

[19]LiBY, LiuB, GuoWW, et al., 2018. Ship size extraction for Sentinel-1 images based on dual-polarization fusion and nonlinear regression: push error under one pixel. IEEE Transactions on Geoscience and Remote Sensing, 56(8):4887-4905.

[20]LiaoRX, WuT, ZhangYM, et al., 2024. Vision-based vessel detection for vessel-bridge collision warnings under complex scenes. Journal of Southeast University (English Edition), 40(1):33-40.

[21]LiaoRX, ZhangYM, WangH, et al., 2025. An effective ship detection approach combining lightweight networks with supervised simulation‐to‐reality domain adaptation. Computer‐Aided Civil and Infrastructure Engineering, 40(27):4732-4757.

[22]LiaoRX, ZhangYM, WangH, et al., 2026. Multi-objective optimisation of surveillance camera placement for bridge-ship collision early-warning using an improved non-dominated sorting genetic algorithm. Advanced Engineering Informatics, 69:103918.

[23]LuLJ, DaiF, 2023. Automated visual surveying of vehicle heights to help measure the risk of overheight collisions using deep learning and view geometry. Computer‐Aided Civil and Infrastructure Engineering, 38(2):194-210.

[24]LuXT, ZhangWX, XuL, et al., 2023. A lateral pressure prediction model for bottom-up pumping of SCC in large-diameter steel tubes based on Bernoulli’s Principle. Case Studies in Construction Materials, 19:e02470.

[25]MaHP, ZhangYJ, SunSY, et al., 2024. Weighted multi-error information entropy based you only look once network for underwater object detection. Engineering Applications of Artificial Intelligence, 130:107766.

[26]MuZH, QinY, YuCC, et al., 2023. Adaptive cropping shallow attention network for defect detection of bridge girder steel using unmanned aerial vehicle images. Journal of Zhejiang University-SCIENCE A, 24(3):243-256.

[27]NguyenT, KashaniA, NgoT, et al., 2019. Deep neural network with high‐order neuron for the prediction of foamed concrete strength. Computer‐Aided Civil and Infrastructure Engineering, 34(4):316-332.

[28]NiFT, ZhangJ, ChenZQ, 2019. Zernike‐moment measurement of thin‐crack width in images enabled by dual‐scale deep learning. Computer‐Aided Civil and Infrastructure Engineering, 34(5):367-384.

[29]PallottaG, VespeM, BryanK, 2013. Vessel pattern knowledge discovery from AIS data: a framework for anomaly detection and route prediction. Entropy, 15(6):2218-2245.

[30]PedersenPT, ChenJ, ZhuL, 2020. Design of bridges against ship collisions. Marine Structures, 74:102810.

[31]RenYB, LiXF, XuH, 2022. A deep learning model to extract ship size from Sentinel-1 SAR images. IEEE Transactions on Geoscience and Remote Sensing, 60:5203414.

[32]SazonovKE, 2011. Navigation challenges for large-size ships in ice conditions. Ships and Offshore Structures, 6(3):231-238.

[33]ShaYY, AmdahlJ, LiuK, 2019. Design of steel bridge girders against ship forecastle collisions. Engineering Structures, 196:109277.

[34]ShaoYC, JinYB, HuangZL, et al., 2024. A learning-based control pipeline for generic motor skills for quadruped robots. Journal of Zhejiang University-SCIENCE A, 25(6):443-454.

[35]ShenS, SadoughiM, LiM, et al., 2020. Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries. Applied Energy, 260:114296.

[36]UrazghildiievI, RagnarssonR, RidderstromP, et al., 2007. Vehicle classification based on the radar measurement of height profiles. IEEE Transactions on Intelligent Transportation Systems, 8(2):245-253.

[37]VolkR, StengelJ, SchultmannF, 2014. Building information modeling (BIM) for existing buildings—literature review and future needs. Automation in Construction, 38:109-127.

[38]WangJD, MaXL, ZhuXH, et al., 2025. Kinematic modeling and stability analysis for a wind turbine blade inspection robot. Journal of Zhejiang University-SCIENCE A, 26(2):121-137.

[39]WangLL, YangLM, HuangDJ, et al., 2008. An impact dynamics analysis on a new crashworthy device against ship-bridge collision. International Journal of Impact Engineering, 35(8):895-904.

[40]WuB, YipTL, YanXP, et al., 2019. Fuzzy logic based approach for ship-bridge collision alert system. Ocean Engineering, 187:106152.

[41]XuHR, YinJN, ZhangN, 2025. Transformer-based deformation measurement of underground structures from a single-camera video. Automation in Construction, 172:106070.

[42]YeXW, JinT, AngPP, et al., 2021. Computer vision‐based monitoring of the 3‐D structural deformation of an ancient structure induced by shield tunneling construction. Structural Control and Health Monitoring, 28(4):e2702.

[43]YeXW, ZhangXL, ZhangHQ, et al., 2023. Prediction of lining upward movement during shield tunneling using machine learning algorithms and field monitoring data. Transportation Geotechnics, 41:101002.

[44]YoonH, ShinJ, Spencer JrBF, 2018. Structural displacement measurement using an unmanned aerial system. Computer‐Aided Civil and Infrastructure Engineering, 33(3):183-192.

[45]YurdakulO, KüçüksuGN, SaydamAZ, et al., 2021. A decision-making process for the selection of better ship main dimensions by a Pareto frontier solution. Ocean Engineering, 239:109908.

[46]ZhaiGH, XuYJ, SpencerBF, 2025. Bidirectional graphics-based digital twin framework for quantifying seismic damage of structures using deep learning networks. Structural Health Monitoring, 24(1):86-110.

[47]ZhangL, ChenPF, LiMX, et al., 2022. A data-driven approach for ship-bridge collision candidate detection in bridge waterway. Ocean Engineering, 266:113137.

[48]ZhangYM, d’AvigneauAM, HadjidemetriouGM, et al., 2024. Bayesian dynamic modelling for probabilistic prediction of pavement condition. Engineering Applications of Artificial Intelligence, 133:108637.

[49]ZhangYM, LiHQ, WangH, 2025. Data-driven wind-induced response prediction for slender civil infrastructure: progress, challenges and opportunities. Structures, 74:108650.