Automated Detection of Sewer Pipe Defects Based on Cost-Sensitive Convolutional Neural Network

Regular inspection and repair of drainage pipes is an important part of urban construction. Currently, many classification methods have been used for defect diagnosis using images inside pipelines. However, most of these classification models train the classifier with the goal of maximizing accuracy without considering the unequal error classification cost in defect diagnosis. In this study, the authors analyze the characteristics of sewer pipeline defect detection and design an automated detection framework based on the cost-sensitive deep convolutional neural network (CNN). The method makes the CNN network cost sensitive by introducing learning theories at the structural and loss levels of the network. To minimize misclassification costs, the authors propose a new auxiliary loss function Cost-Mean Loss, which allows the model to obtain the original parameters of the network to maximize the accuracy and improve the performance of the model by minimizing total misclassification costs in the learning process. Theoretical analysis shows that the new auxiliary loss function can be applied to the classification task to optimize the expected value of misclassification costs. The inspection images collected from multiple drainage pipes were used to train and test the network. Results show that after the cost-sensitive strategy was added, the defect detection rate decreased from 2.1% to 0.45%. Moreover, the model with Cost-Mean Loss has better performance than the original model.

[1]  Samuel T. Ariaratnam,et al.  Innovative method for assessment of underground sewer pipe condition , 2006 .

[2]  Hsuan-Tien Lin,et al.  Cost-Aware Pre-Training for Multiclass Cost-Sensitive Deep Learning , 2015, IJCAI.

[3]  Mohammed Bennamoun,et al.  Cost-Sensitive Learning of Deep Feature Representations From Imbalanced Data , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[4]  Jack Chin Pang Cheng,et al.  Automated detection of sewer pipe defects in closed-circuit television images using deep learning techniques , 2018, Automation in Construction.

[5]  F. Cherqui,et al.  The consistency of visual sewer inspection data , 2013 .

[6]  Amal Elsayed Aboutabl,et al.  A New Image-Based Model For Predicting Cracks In Sewer Pipes , 2013 .

[7]  Tarek Zayed,et al.  Automated defect detection tool for closed circuit television (cctv) inspected sewer pipelines , 2018 .

[8]  Hsuan-Tien Lin,et al.  Cost-Sensitive Deep Learning with Layer-Wise Cost Estimation , 2016, 2020 International Conference on Technologies and Applications of Artificial Intelligence (TAAI).

[9]  Chen Huang,et al.  Learning Deep Representation for Imbalanced Classification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Osama Moselhi,et al.  Automated detection of surface defects in water and sewer pipes , 1999 .

[11]  Shuai Guo,et al.  Sewer damage detection from imbalanced CCTV inspection data using deep convolutional neural networks with hierarchical classification , 2019, Automation in Construction.

[12]  Nuno Vasconcelos,et al.  Cost-Sensitive Support Vector Machines , 2012, Neurocomputing.

[13]  Richard Nelson,et al.  Process for Evaluating Sanitary Sewer Pipe and Manhole Condition Assessment Data , 2010 .

[14]  Xiao-Lei Zhang.  Speech separation by cost-sensitive deep learning , 2017, 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

[15]  Amal Elsayed Aboutabl,et al.  A New Image Model for Predicting Cracks in Sewer Pipes based on Time , 2014 .

[16]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Mohammad Khalilia,et al.  Predicting disease risks from highly imbalanced data using random forest , 2011, BMC Medical Informatics Decis. Mak..

[18]  Ming-Der Yang,et al.  Segmenting ideal morphologies of sewer pipe defects on CCTV images for automated diagnosis , 2009, Expert Syst. Appl..

[19]  Jiewei Jiang,et al.  Automatic diagnosis of imbalanced ophthalmic images using a cost-sensitive deep convolutional neural network , 2017, BioMedical Engineering OnLine.

[20]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[21]  T. Davies,et al.  Sewer pipe deformation assessment by image analysis of video surveys , 1998, Pattern Recognit..

[22]  Andrew K. C. Wong,et al.  Classification of Imbalanced Data: a Review , 2009, Int. J. Pattern Recognit. Artif. Intell..

[23]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[24]  Richard M. Everson,et al.  Automated Detection of Faults in Wastewater Pipes from CCTV Footage by Using Random Forests , 2016 .

[25]  Mahmoud R. Halfawy,et al.  Automated defect detection in sewer closed circuit television images using histograms of oriented gradients and support vector machine , 2014 .

[26]  Zheng Liu,et al.  State of the art review of inspection technologies for condition assessment of water pipes , 2013 .

[27]  Dulcy M. Abraham,et al.  Automated defect classification in sewer closed circuit television inspections using deep convolutional neural networks , 2018, Automation in Construction.