Image‐based post‐disaster inspection of reinforced concrete bridge systems using deep learning with Bayesian optimization

Computer-Aided Civil and Infrastructure Engineering - Tập 34 Số 5 - Trang 415-430 - 2019
Xiao Liang1
1Department of Civil, Structural and Environmental Engineering, University at Buffalo–The State University of New York, NY, USA

Tóm tắt

AbstractMany bridge structures, one of the most critical components in transportation infrastructure systems, exhibit signs of deteriorations and are approaching or beyond the initial design service life. Therefore, structural health inspections of these bridges are becoming critically important, especially after extreme events. To enhance the efficiency of such an inspection, in recent years, autonomous damage detection based on computer vision has become a research hotspot. This article proposes a three‐level image‐based approach for post‐disaster inspection of the reinforced concrete bridge using deep learning with novel training strategies. The convolutional neural network for image classification, object detection, and semantic segmentation are, respectively, proposed to conduct system‐level failure classification, component‐level bridge column detection, and local damage‐level damage localization. To enable efficient training and prediction using a small data set, the model robustness is a crucial aspect to be taken into account, generally through its hyperparameters’ selection. This article, based on Bayesian optimization, proposes a principled manner of such selection, with which very promising results (well over 90% accuracies) and robustness are observed on all three‐level deep learning models.

Từ khóa


Tài liệu tham khảo

10.1016/j.jsv.2016.10.043

10.1061/(ASCE)0887-3801(2003)17:4(255)

ASCE Infrastructure Report Card(2017). Retrieved fromhttps://www.infrastructurereportcard.org/

10.1109/TPAMI.2016.2644615

10.1007/978-0-387-45528-0

Brochu E. Cora V. M. &DeFreitas N.(2010).A tutorial on Bayesian optimization of expensive cost functions with application to active user modeling and hierarchical reinforcement learning arXiv preprint arXiv:1012.2599.

Calderone A., 2001, Behavior of reinforced concrete bridge columns having varying aspect ratios and varying lengths of confinement

10.1111/mice.12263

10.1111/mice.12334

Chavali N. Agrawal H. Mahendru A. &Batra D.(2015).Object‐proposal evaluation protocol is “gameable.”arXiv:1505.05836.

10.5244/C.27.32

10.1111/mice.12257

Dalal N. &Triggs B.(2005).Histograms of oriented gradients for human detection. InIEEE Computer Society Conference on Computer Vision and Pattern Recognition CVPR’05. Vol. 1 San Diego CA: IEEE 886–893.https://doi.org/10.1109/CVPR.2005.177

Deng J. Dong W. Socher R. Li L. J. Li K. &Li F.(2009).ImageNet: A large‐scale hierarchical image database. InIEEE International Conference on Computer Vision & Pattern Recognition (CVPR) San Diego CA: IEEE 248–255.

Eigen D. &Fergus R.(2015).Predicting depth surface normals and semantic labels with a common multi‐scale convolutional architecture. InProceedings of IEEE International Conference on Computer Vision San Diego CA: IEEE 2650–2658.

Esmaeily A., 2005, Behavior of reinforced concrete columns under variable axial loads: Analysis, ACI Structural Journal, 102, 736

10.1007/s11263-009-0275-4

10.1002/9781118443118

Feng C., 2017, Computing in Civil Engineering, 298

10.1016/j.ymssp.2016.11.021

10.5194/nhess-15-1087-2015

10.1111/mice.12363

10.1016/j.aei.2012.06.005

Girshick R.(2015).Fast R‐CNN. InProceedings of the IEEE International Conference on Computer Vision 1440–1448.

Girshick R. Donahue J. Darrell T. &Malik J.(2014).Rich feature hierarchies for accurate object detection and semantic segmentation. InProceedings of IEEE Conference on Computer Vision and Pattern Recognition 580–587.

Goodfellow I., 2016, Deep learning

He K. Zhang X. Ren S. &Sun J.(2016).Deep residual learning for image recognition. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition 770–778.

Hong S. Noh H. &Han B.(2015).Decoupled deep neural network for semi‐supervised semantic segmentation. InProceedings 28th International Conference on Neural Information Processing Systems 1495–1503.

10.1109/TPAMI.2015.2465908

Hosang J. Benenson R. &Schiele B.(2014).How good are detection proposals really?Presented atProceedings of British Machine Vision Conference Nottingham England.

Hoskere V. Narazaki Y. Hoang T. &SpencerJr. B.(2018).Vision‐based structural inspection using multiscale deep convolutional neural networks.arXiv preprint arXiv:1805.01055.

10.1080/15732470801945930

10.1109/LGRS.2013.2257676

10.1016/j.aei.2015.01.008

10.1260/1369-4332.17.3.303

Kohavi R., 1998, Confusion matrix, Machine Learning, 30, 271

10.3233/ICA-170551

Krizhevsky A., 2012, ImageNet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems, 1097

10.1162/neco.1989.1.4.541

10.1109/5.726791

10.1111/mice.12351

10.1111/mice.12313

Long J. Shelhamer E. &Darrell T.(2015).Fully convolutional networks for semantic segmentation. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition 3431–3440.

Murphy K. P., 2012, Machine learning: A probabilistic perspective

10.1111/mice.12359

Nagi J. Ducatelle F. Di Caro G. A. Cireşan D. Meier U. Giusti A. …Gambardella L. M.(2011).Max‐pooling convolutional neural networks for vision‐based hand gesture recognition. InIEEE International Conference on Signal & Image Processing Applications (ICSIPA) 342–347.

Nair V. &Hinton G. E.(2010).Rectified linear units improve restricted Boltzmann machines. InProceedings of the 27th International Conference on Machine Learning (ICML‐10) 807–814.

Narazaki Y. Hoskere V. Hoang T. A. &SpencerJr. B. F.(2018).Automated vision‐based bridge component extraction using multiscale convolutional neural networks.arXiv preprint arXiv:1805.06042.

10.1109/ICCV.2015.178

10.3233/ICA-170538

10.1109/TSMC.1979.4310076

10.1002/tal.1400

10.1016/j.engstruct.2017.10.070

10.14359/51689560

Rasmussen C. E., 2006, Gaussian processes for machine learning

10.1109/TPAMI.2016.2577031

Rose P. Aaron B. Tamir D. E. Lu L. Hu J. &Shi H.(2014).Supervised computer‐vision‐based sensing of concrete bridges for crack‐detection and assessment(No. 14–3857).

Sideris P.(2012).Seismic analysis and design of precast concrete segmental bridges. Thesis State University of New York at Buffalo.

Simonyan K. &Zisserman A. (2014).Very deep convolutional networks for large‐scale image recognition.arXiv preprint arXiv:1409.1556.

Snoek J., 2012, Proceedings of the 25th International Conference on Neural Information Processing Systems

10.1007/978-3-319-14249-4_64

Srivastava N., 2014, Dropout: A simple way to prevent neural networks from overfitting, Journal of Machine Learning Research, 15, 1929

10.1117/12.2295954

10.1109/CVPR.2015.7298594

10.1109/CVPR.2016.308

10.1061/(ASCE)CP.1943-5487.0000334

10.1007/s11263-013-0620-5

Veletzos M. Panagiutou M. Restrepo J. &Sahs S.(2008).Visual inspection & capacity assessment of earthquake damaged reinforced concrete bridge elements(No. CA08‐0284). California Department of Transportation Division of Research and Innovation.

10.1016/j.isprsjprs.2017.03.001

10.1109/CVPR.2001.990517

10.1111/mice.12367

10.1007/s00138-009-0189-8

10.1111/mice.12141

Yeum C. M., 2016, International Conference on Smart Infrastructure and Construction

10.1002/stc.1850

10.1111/mice.12297

Zheng S., 2015, Proceedings of the IEEE International Conference on Computer Vision, 1529

10.1061/(ASCE)CP.1943-5487.0000053

10.1016/j.autcon.2011.03.004

Thông tin
Thông tin xuất bản

Computer-Aided Civil and Infrastructure Engineering

Tập 34 Số 5

415-430

Thông tin tác giả