Abstract
Detecting damage to concrete dams, such as cracks, spalling, and precipitates, using traditional methods is challenging. In this study, we propose an automatic multiple-damage detection method for concrete dams based on faster region-based convolutional neural networks, which is an end-to-end object detection algorithm that can predict object categories and bounds. In this study, Residual Network-101 is fine-tuned and used to replace the original feature extraction network to enhance the feature-extraction capability. To improve the performance of the model for dam-damage detection, scales and aspect ratios are specifically designed based on the characteristics of dam damage. The proposed damage-detection approach is verified using a dataset containing 912 images (900 × 600 pixels) obtained from different concrete dams. The results reveal that the proposed method can efficiently identify and locate all types of damage in the dam images. The average detection accuracy for cracks, spalling, and precipitates is 0.868, 0.948, and 0.847, respectively. This study can provide reliable technical support for the safe operation of concrete dams.
Similar content being viewed by others
References
Li MC, Shen Y, Ren QB, Li H (2019) A new distributed time series evolution prediction model for dam deformation based on constituent elements. Adv Eng Inform 39:41–52
Wu ZR, Gu CS (2005) Trouble detection and health diagnosis of large hydraulic concrete structure. Higher Education Press, Beijing (in Chinese)
Su HZ, Li JY, Wen ZP, Zhou FF (2018) A bi-criteria combined evaluation approach for reinforcement effect of gravity dam with cracks. Int J Solids Struct 147:238–253
Leung CKY, Olson N, Wan KT, Meng AD (2005) Theoretical modeling of signal loss versus crack opening for a novel crack sensor. J Eng Mech 131:777–790
Zhao SZ, Kang F, Li JJ, Ma CB (2021) Structural health monitoring and inspection of dams based on UAV photogrammetry with image 3D reconstruction. Automat Constr 130:103832
Bao TF, Wang JL, Yao YA (2010) A fiber optic sensor for detecting and monitoring cracks in concrete structures. Sci China Technol Sc 53:3045–3050
Zhao JL, Bao TF, Amjad U (2015) Optical fiber sensing of small cracks in isotropic homogeneous materials. Sensor Actuat a-Phys 225:133–138
Zhao ZY, Chen B, Wu ZR, Zhang S (2021) Multi-sensing investigation of crack problems for concrete dams based on detection and monitoring data: a case study. Measurement 175:109137
Chevva K, Shirke JM, Ghosh N (2008) Assessment of concrete quality using non-destructive techniques, Ghatghar project, Maharashtra, India. B Eng Geol Environ 67:65–70
Hui L, Haitao M (2011) Application of ground penetrating radar in dam body detection. Procedia Engineering 26:1820–1826
Feng DM, Feng MQ (2018) Computer vision for SHM of civil infrastructure: from dynamic response measurement to damage detection: a review. Eng Struct 156:105–117
Cha YJ, You K, Choi W (2016) Vision-based detection of loosened bolts using the Hough transform and support vector machines. Automat Constr 71:181–188
Sinha SK, Fieguth PW (2006) Automated detection of cracks in buried concrete pipe images. Automat Constr 15:58–72
Abdel-Qader I, Pashaie-Rad S, Abudayyeh O, Yehia S (2006) PCA-Based algorithm for unsupervised bridge crack detection. Adv Eng Softw 37:771–778
Li G, Zhao XX, Du K, Ru F, Zhang YB (2017) Recognition and evaluation of bridge cracks with modified active contour model and greedy search-based support vector machine. Automat Constr 78:51–61
Fan XN, Wu JJ, Shi PF, Zhang XW, Xie YJ (2018) A novel automatic dam crack detection algorithm based on local-global clustering. Multimed Tools Appl 77:26581–26599
Shi PF, Fan XN, Ni JJ, Wang GR (2016) A detection and classification approach for underwater dam cracks. Struct Health Monit 15:541–554
Ye XW, Jin T, Yun CB (2019) A review on deep learning-based structural health monitoring of civil infrastructures. Smart Struct Syst 24:567–585
Spencer BF, Hoskere V, Narazaki Y (2019) Advances in computer vision-based civil infrastructure inspection and monitoring. Engineering-Prc 5:199–222
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444
Dorafshan S, Thomas RJ, Maguire M (2018) Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete. Constr Build Mater 186:1031–1045
Cha YJ, Choi W, Buyukozturk O (2017) Deep learning-based crack damage detection using convolutional neural networks. Comput-Aided Civ Inf 32(5):361–378
Xu Y, Bao YQ, Chen JH, Zuo WM, Li H (2019) Surface fatigue crack identification in steel box girder of bridges by a deep fusion convolutional neural network based on consumer-grade camera images. Struct Health Monit 18:653–674
Hoang ND, Nguyen QL, Tran VD (2018) Automatic recognition of asphalt pavement cracks using metaheuristic optimized edge detection algorithms and convolution neural network. Automat Constr 94:203–213
Li G, Ren XL, Qiao WT, Ma B, Li Y (2020) Automatic bridge crack identification from concrete surface using ResNeXt with postprocessing. Struct Control Hlth 27(11):e2620
Gopalakrishnan K, Khaitan SK, Choudhary A, Agrawal A (2017) Deep convolutional neural networks with transfer learning for computer vision-based data-driven pavement distress detection. Constr Build Mater 157:322–330
Atha DJ, Jahanshahi MR (2018) Evaluation of deep learning approaches based on convolutional neural networks for corrosion detection. Struct Health Monit 17:1110–1128
Wang NN, Zhao XF, Zhao P, Zhang Y, Zou Z, Ou JP (2019) Automatic damage detection of historic masonry buildings based on mobile deep learning. Automat Constr 103:53–66
Xu Y, Wei SY, Bao YQ, Li H (2019) Automatic seismic damage identification of reinforced concrete columns from images by a region-based deep convolutional neural network. Struct Control Hlth 26(3):e2313
Cha YJ, Choi W, Suh G, Mahmoudkhani S, Buyukozturk O (2018) Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types. Comput-Aided Civ Inf 33(9):731–747
Xue YD, Li YC (2018) A fast detection method via region-based fully convolutional neural networks for shield tunnel lining defects. Comput-Aided Civ Inf 33(8):638–654
Hoskere V, Narazaki Y, Hoang TA, Spencer BF (2020) MaDnet: multi-task semantic segmentation of multiple types of structural materials and damage in images of civil infrastructure. J Civ Struct Health 10:757–773
Bang S, Park S, Kim H, Kim H (2019) Encoder-decoder network for pixel-level road crack detection in black-box images. Comput-Aided Civ Inf 34(8):713–727
Chow JK, Su Z, Wu J, Tan PS, Mao X, Wang YH (2020) Anomaly detection of defects on concrete structures with the convolutional autoencoder. Adv Eng Inform 45:101105
Li YT, Bao TF, Chen H, Zhang K, Shu XS, Chen ZX et al (2021) A large-scale sensor missing data imputation framework for dams using deep learning and transfer learning strategy. Measurement 178:109377
Wu ZR, Li J, Gu CS, Su HZ (2007) Review on hidden trouble detection and health diagnosis of hydraulic concrete structures. Sci China Ser E 50:34–50
Akbar MA, Qidwai U, Jahanshahi MR (2019) An evaluation of image-based structural health monitoring using integrated unmanned aerial vehicle platform. Struct Control Hlth 26(1):e2276
Feng CC, Zhang H, Wang HR, Wang S, Li YL (2020) Automatic pixel-level crack detection on dam surface using deep convolutional network. Sensors-Basel 20:2069
Li L, Zhang H, Pang J, et al (2019) Dam surface crack detection based on deep learning. In: Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence 738–743
Ren SQ, He KM, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE T Pattern Anal 39:1137–1149
He KM, Zhang XY, Ren SQ, Sun J (2016) Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp 770–778
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S et al (2015) ImageNet large scale visual recognition challenge. Int J Comput Vision 115:211–252
Pan SJ, Yang QA (2010) A survey on transfer learning. IEEE T Knowl Data En 22:1345–1359
Zhuang FZ, Qi ZY, Duan KY, Xi DB, Zhu YC, Zhu HS et al (2021) A comprehensive survey on transfer learning. Proceed IEEE 109(1):43–76
Tajbakhsh N, Shin JY, Gurudu SR, Hurst RT, Kendall CB, Gotway MB et al (2016) Convolutional neural networks for medical image analysis: full training or fine tuning? Ieee T Med Imaging 35:1299–1312
Siddiqi R (2019) Effectiveness of transfer learning and fine tuning in automated fruit image classification. In: Proceedings of the 2019 3rd International Conference on Deep Learning Technologies, pp 91–100
Kumar A, Kim J, Lyndon D, Fulham M, Feng DG (2017) An ensemble of fine-tuned convolutional neural networks for medical image classification. IEEE J Biomed Health 21:31–40
Najibi M, Samangouei P, Chellappa R, Davis LS (2017) SSH: single stage headless face detector. In: Proceedings of the IEEE international conference on computer vision, pp 4885–4894
Song D, Qiao Y, Corbetta A (2017) Depth driven people counting using deep region proposal network. In: 2017 IEEE International Conference on Information and Automation (ICIA), pp 416–421
Zhang L, Lin L, Liang X, He K (2016) Is faster R-CNN doing well for pedestrian detection? European conference on computer vision. Springer, Cham, pp 443–457
Zhang LL, Zhang Y, Zhang Z, Shen J, Wang HB (2019) Real-time water surface object detection based on improved faster R-CNN. Sensors-Basel 19(16):3523
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580–587
Girshick R (2015) Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1440–1448
Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2010) The pascal visual object classes (VOC) challenge. Int J Comput Vision 88:303–338
Everingham M, Zisserman A, Williams CKI et al (2008) The 2005 pascal visual object classes challenge. In: Machine Learning Challenges Workshop. Springer, Heidelberg, pp 117–176
Simonyan. K, Zisserman. A (2015) Very deep convolutional networks for large-scale image recognition. In: Proc. Int. Conf. Learning Represen. arXiv preprint. arXiv:1409.1556
Howard AG, Zhu ML, Chen B, Kalenichenko D, Wang WJ, Weyand T et al (2017) MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint. arXiv:1704.04861
Gao SH, Cheng MM, Zhao K, Zhang XY, Yang MH, Torr P (2021) Res2Net: a new multi-scale backbone architecture. IEEE T Pattern Anal 43:652–662
Redmon J, Farhadi A (2018) YOLOv3: An Incremental Improvement. IEEE conference on Computer Vision and Pattern Recognition (Cvpr). arXiv preprint. arXiv:1804.02767
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY et al (2016) SSD: single shot MultiBox detector. Lect Notes Comput Sc 9905:21–37
Acknowledgements
This work was supported by the National Key R & D Program of China (2016YFC0401600), the National Natural Science Foundation of China (51779035, 52079022, 51769033 and 51979027), the Fundamental Research Funds for the Central Universities (DUT21TD106).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Huang, B., Zhao, S. & Kang, F. Image-based automatic multiple-damage detection of concrete dams using region-based convolutional neural networks. J Civil Struct Health Monit 13, 413–429 (2023). https://doi.org/10.1007/s13349-022-00650-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13349-022-00650-9