Abstract
The operation of a sewer pipeline network affects the urban drainage effect, and identifying the defects of the pipe network is very significant to accurately evaluate the condition of the pipeline network. Closed-circuit television detection has been widely used in urban sewer pipeline network inspection. However, manual discrimination requires professionals to have enough knowledge reserves, which is subjective, laborious, and time-consuming. It is necessary to realize automation and intelligence of defect classification of the sewer pipeline network. An intelligent identification model for sewer pipeline network defects is constructed based on an improved RegNetY network and gradient-weighted class activation mapping (Grad-CAM). The defects are classified and visualized. First, data augmentation is used to deal with data imbalance. Then, LeakyReLU is used as the activation function to improve the RegNetY network. Finally, the training features of the improved RegNetY network are visualized using Grad-CAM. The engineering application results show that the improved RegNetY is more competitive than other types of deep neural networks in defect classification, which can improve the inspection efficiency of engineers. The Grad-CAM can visualize the specific location of defects, which is beneficial to understanding the defect information in images intuitively.
Similar content being viewed by others
Data availability
Data will be made available on request.
References
Lyu H, Ni GH, Tian FQ (2018) Impacts of drainage pipe network complexity on urban stormwater modeling. J Hydroelectr Eng 37(11):97–106. https://doi.org/10.11660/slfdxb.20181110. (in Chinese)
Zhang ML, Shen YM, Shen D (2007) Contrast study of unsteady flow mathematical model for rain pipeline networks of urban drainage system. J Hydroelectr Eng 26(5):80–85. https://doi.org/10.3969/j.issn.1003-1243.2007.05.016. (in Chinese)
Jagai JS, Deflorio-Barker S, Lin CJ et al (2017) Sanitary sewer overflows and emergency room visits for gastrointestinal illness: analysis of Massachusetts data, 2006–2007. Environ Health Perspect 125(11):117007. https://doi.org/10.1289/EHP2048
Wang JL, Deng YL, Li Y et al (2020) A review on detection and defect identification of drainage pipeline. Sci Technol Eng 20(33):13520–13528. https://doi.org/10.3969/j.issn.1671-1815.2020.33.002. (in Chinese)
He M, Qi CC, Chen JX et al (2021) Intelligent auxiliary classification method for drainage pipeline defects based on inspection images. Sci Technol Eng 21(35):15144–15151. https://doi.org/10.3969/j.issn.1671-1815.2021.35.035. (in Chinese)
Duanshun L, Anran C, Shuai G (2019) Sewer damage detection from imbalanced CCTV inspection data using deep convolutional neural networks with hierarchical classification. Autom Constr 101:199–208. https://doi.org/10.1016/j.autcon.2019.01.017
Srinath SK, Dulcy MA, Mohammad RJ et al (2018) Automated defect classification in sewer closed circuit television inspections using deep convolutional neural networks. Autom Constr 91:273–283. https://doi.org/10.1016/j.autcon.2018.03.028
Cheng JCP, Wang M (2018) Automated detection of sewer pipe defects in closed-circuit television images using deep learning techniques. Autom Constr 95:155–171. https://doi.org/10.1016/j.autcon.2018.08.006
Wang M, Cheng JCP (2020) A unified convolutional neural network integrated with conditional random field for pipe defect segmentation. Comput Aided Civ Infrastruct Eng 35(2):162–177. https://doi.org/10.1111/mice.12481
Zhou QQ, Situ ZX, Teng S et al (2021) Intelligent detection and classification of drainage pipe defects based on convolutional neural networks. China Water Wastewater 37(21):114–118. https://doi.org/10.19853/j.zgjsps.1000-4602.2021.21.018. (in Chinese)
Kruachottikul P, Cooharojananone N, Phanomchoeng G et al (2021) Deep learning-based visual defect-inspection system for reinforced concrete bridge substructure: a case of Thailand’s department of highways. J Civ Struct Heal Monit 11(4):949–965. https://doi.org/10.1007/s13349-021-00490-z
Ren QB, Li MC, Shen Y et al (2021) Pixel-level shape segmentation and feature quantification of hydraulic concrete cracks based on digital images. J Hydroelectr Eng 40(2):234–246. https://doi.org/10.11660/slfdxb.20210224. (in Chinese)
Sharma S, Sen S (2020) One-dimensional convolutional neural network-based damage detection in structural joints. J Civ Struct Health Monit 10(5):1057–1072. https://doi.org/10.1007/s13349-020-00434-z
Ruffels A, Gonzalez I, Karoumi R (2020) Model-free damage detection of a laboratory bridge using artificial neural networks. J Civ Struct Health Monit 10(2):183–195. https://doi.org/10.1007/s13349-019-00375-2
Tran VP, Tran TS, Lee HJ et al (2020) One stage detector (RetinaNet)-based crack detection for asphalt pavements considering pavement distresses and surface objects. J Civ Struct Health Monit 11(1):205–222. https://doi.org/10.1007/s13349-020-00447-8
Sunil KS, Paul WF (2005) Neuro-fuzzy network for the classification of buried pipe defects. Autom Constr 15(1):73–83. https://doi.org/10.1016/j.autcon.2005.02.005
Su TC, Yang MD, Wu TC et al (2011) Morphological segmentation based on edge detection for sewer pipe defects on CCTV images. Expert Syst Appl 38(10):13094–13114. https://doi.org/10.1016/j.eswa.2011.04.116
Alaa H, Mazen A, Firas A et al (2018) Automated defect detection tool for closed circuit television (CCTV) inspected sewer pipelines. Autom Constr 89:99–109. https://doi.org/10.1016/j.autcon.2018.01.004
Xie Q, Li D, Xu J et al (2019) Automatic detection and classification of sewer defects via hierarchical deep learning. IEEE Trans Autom Sci Eng 16(4):1836–1847. https://doi.org/10.1109/TASE.2019.2900170
Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25(2):1097–1105. https://doi.org/10.1145/3065386
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. In: Proceedings of the international conference on learning representations, pp 1–14. https://doi.org/10.48550/arXiv.1409.1556
Wang HP, An GF, Xie GY (2014) Interpretation of technical regulations for inspection and evaluation of urban drainage pipelines (CJJ181—2012). Water Supply Sewerage 50(2):124–127. https://doi.org/10.3969/j.issn.1002-8471.2014.02.032. (in Chinese)
He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: Conference on computer vision and pattern recognition, pp 770–778. https://doi.org/10.1109/CVPR.2016.90
Tan M, Le QV (2021) EfficientNetV2: smaller models and faster training. In: Proceedings of the 38th international conference on machine learning, pp 10096–10106. https://doi.org/10.48550/arXiv.2104.00298
Sandler M, Howard A, Zhu M et al (2018) MobileNetV2: inverted residuals and linear bottlenecks. In: Conference on computer vision and pattern recognition (CVPR), pp 4510–4520. https://doi.org/10.1109/CVPR.2018.00474
Huang G, Liu Z, Laurens V et al (2017) Densely connected convolutional networks. In: Conference on computer vision and pattern recognition, pp 2261–2269. https://doi.org/10.1109/CVPR.2017.243
Ma N, Zhang X, Zheng T et al (2018) ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Proceedings of the 15th European conference on computer vision, 2018, pp 122–138. https://doi.org/10.48550/arXiv.1807.11164
Radosavovi I, Kosaraju RP, Girshick R et al (2020) Designing network design spaces. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp 10425–10433. https://doi.org/10.1109/CVPR42600.2020.01044
Bowen B, Otkrist G, Nikhil N et al (2017) Designing neural network architectures using reinforcement learning. In: Proceedings of international conference on learning representations, pp 1–18. https://doi.org/10.48550/arXiv.1611.02167
Li L, Zhang S, Wang B (2021) Apple leaf disease identification with a small and imbalanced dataset based on lightweight convolutional networks. Sensors 22(1):173–173. https://doi.org/10.3390/s22010173
Jie H, Li S, Gang S et al (2019) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42(8):2011–2023. https://doi.org/10.1109/TPAMI.2019.2913372
Selvaraju RR, Cogswell M, Das A et al (2020) Grad-CAM: visual explanations from deep networks via gradient-based localization. Int J Comput Vis 128(2):336–359. https://doi.org/10.1007/s11263-019-01228-7
Zhou B, Khosla A, Lapedriza A et al (2016) Learning deep features for discriminative localization. In: IEEE conference on computer vision and pattern recognition, pp 2921–2929. https://doi.org/10.1109/CVPR.2016.319
Hou QS, Xing JS (2020) SSD object detection algorithm based on KL loss and Grad-CAM. Acta Electron Sin 48(12):2409–2416. https://doi.org/10.3969/j.issn.0372-2112.2020.12.017. (in Chinese)
Feng XS, Shen Y, Wang DQ (2021) A survey on the development of image data augmentation. Comput Sci Appl 11(2):370–382. https://doi.org/10.12677/CSA.2021.112037. (in Chinese)
Acknowledgements
This research was jointly funded by the National Natural Science Foundation of China (Grant nos. 51879185 and 52179139), and the Open Fund of Hubei Key Laboratory of Construction and Management in Hydropower Engineering (Grant no. 2020KSD06).
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
Li, M., Li, M., Ren, Q. et al. Intelligent identification and classification of sewer pipeline network defects based on improved RegNetY network. J Civil Struct Health Monit 13, 547–560 (2023). https://doi.org/10.1007/s13349-022-00660-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13349-022-00660-7