ABSTRACT
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.
- Koo, D. H., and Ariaratnam, S. T. 2006. Innovative method for assessment of underground sewer pipe condition. Automation in construction, 15(4), 479--488. DOI= http://dx.doi.org/10.1016/j.autcon.2005.06.007.Google Scholar
- Liu, Z., and Kleiner, Y. 2013. State of the art review of inspection technologies for condition assessment of water pipes. Measurement, 46(1), 1--15. DOI= http://dx.doi.org/10.1016/j.measurement.2012.05.032.Google Scholar
- Rahman, S., and Vanier, D. J. 2004. An evaluation of condition assessment protocols for sewer management. Tech. rep. National Research Council Canada.Google Scholar
- Dirksen, J., Clemens, F. H. L. R., Korving, H., Cherqui, F., Le Gauffre, P., Ertl, T., ... and Snaterse, C. T. M. 2013. The consistency of visual sewer inspection data. Structure and Infrastructure Engineering, 9(3), 214--228. DOI= http://dx.doi.org/10.1080/15732479.2010.541265.Google ScholarCross Ref
- Khalilia, M., Chakraborty, S., and Popescu, M. 2011. Predicting disease risks from highly imbalanced data using random forest. BMC medical informatics and decision making, 11(1), 51. DOI= http://dx.doi.org/10.1186/1472-6947-11-51.Google Scholar
- Sun, Y., Wong, A. K., and Kamel, M. S. 2009. Classification of imbalanced data: A review. International Journal of Pattern Recognition and Artificial Intelligence, 23(04), 687--719. DOI= http://dx.doi.org/10.1186/1472-6947-11-51.Google ScholarCross Ref
- Xu, K., Luxmoore, A. R., and Davies, T. 1998. Sewer pipe deformation assessment by image analysis of video surveys. Pattern Recognition, 31(2), 169--180. DOI= https://doi.org/10.1016/S0031-3203(97)00037-X.Google ScholarCross Ref
- Moselhi, O., and Shehab-Eldeen, T. 1999. Automated detection of surface defects in water and sewer pipes. Automation in Construction, 8(5), 581--588. DOI= https://doi.org/10.1016/S0926-5805(99)00007-2.Google ScholarCross Ref
- Yang, M. D., and Su, T. C. 2009. Segmenting ideal morphologies of sewer pipe defects on CCTV images for automated diagnosis. Expert Systems with Applications, 36(2), 3562--3573. DOI= https://doi.org/10.1016/j.eswa.2008.02.006.Google ScholarDigital Library
- Khalifa, I., Aboutabl, A. E., and Barakat, G. S. A. 2013. A new image-based model for predicting cracks in sewer pipes. Editorial Preface, 4(12). DOI= https://doi.org/10.5120/15238-3779.Google Scholar
- Halfawy, M. R., and Hengmeechai, J. 2014. Automated defect detection in sewer closed circuit television images using histograms of oriented gradients and support vector machine. Automation in Construction, 38, 1--13. DOI= https://doi.org/10.1016/j.autcon.2013.10.012.Google ScholarCross Ref
- Myrans, J., Kapelan, Z., and Everson, R. 2016. Automated detection of faults in wastewater pipes from CCTV footage by using random forests. Procedia engineering, 154, 36--41. DOI= https://doi.org/10.1016/j.proeng.2016.07.416.Google Scholar
- Hawari, A., Alamin, M., Alkadour, F., Elmasry, M., and Zayed, T. 2018. Automated defect detection tool for closed circuit television (cctv) inspected sewer pipelines. Automation in Construction, 89, 99--109. DOI= https://doi.org/10.1016/j.autcon.2018.01.004.Google ScholarCross Ref
- Kumar, S. S., Abraham, D. M., Jahanshahi, M. R., Iseley, T., and Starr, J. 2018. Automated defect classification in sewer closed circuit television inspections using deep convolutional neural networks. Automation in Construction, 91, 273--283. DOI= https://doi.org/10.1016/j.autcon.2018.03.028.Google Scholar
- Cheng, J. C., and Wang, M. 2018. Automated detection of sewer pipe defects in closed-circuit television images using deep learning techniques. Automation in Construction, 95, 155--171. DOI= https://doi.org/10.1016/j.autcon.2018.08.006.Google Scholar
- Li, D., Cong, A., and Guo, S. 2019. Sewer damage detection from imbalanced CCTV inspection data using deep convolutional neural networks with hierarchical classification. Automation in Construction, 101, 199--208. DOI= https://doi.org/10.1016/j.autcon.2019.01.017.Google Scholar
- Chung, Y. A., Lin, H. T., and Yang, S. W.. 2015. Cost-aware pre-training for multiclass cost-sensitive deep learning. Computer Science. DOI= https://arxiv.org/abs/1511.09337.Google Scholar
- Chung, Y. A., and Lin, H. T. 2016. Cost-Sensitive Deep Learning with Layer-Wise Cost Estimation. arXiv preprint arXiv:1611.05134. DOI= https://arxiv.org/abs/1611.05134.Google Scholar
- Khan, S. H., Hayat, M., Bennamoun, M., Sohel, F. A., and Togneri, R. 2017. Cost-sensitive learning of deep feature representations from imbalanced data. IEEE transactions on neural networks and learning systems, 29(8), 3573--3587. DOI= https://doi.org/10.1109/TNNLS.2017.2732482.Google Scholar
- Xie, S., and Tu, Z. 2015. Holistically-nested edge detection. In Proceedings of the IEEE international conference on computer vision (pp. 1395--1403). DOI= https://doi.org/10.1007/s11263--017-1004-z.Google Scholar
- Huang, C., Li, Y., Change Loy, C., and Tang, X. 2016. Learning deep representation for imbalanced classification. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5375--5384). DOI= https://doi.org/ 10.1109/CVPR.2016.580.Google Scholar
- Zhang, X. L. 2017, December. Speech separation by cost-sensitive deep learning. In 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) (pp. 159--162). IEEE. DOI= https://doi.org/10.1109/APSIPA.2017.8282020.Google Scholar
- Jiang, J., Liu, X., Zhang, K., Long, E., Wang, L., Li, W., ... and Liu, Z. 2017. Automatic diagnosis of imbalanced ophthalmic images using a cost-sensitive deep convolutional neural network. Biomedical engineering online, 16(1), 132. DOI= https://doi.org/10.1186/s12938--017-0420--1.Google Scholar
- Nelson, R., Rowe, R., and Varghese, V. 2010. Process for evaluating sanitary sewer pipe and manhole condition assessment data. In Pipelines 2010: Climbing new peaks to infrastructure reliability: Renew, rehab, and reinvest (pp. 743--752). DOI= https://doi.org/ 10.1061/41138(386)72.Google Scholar
- Dalal, N., and Triggs, B. 2005. Histograms of Oriented Gradients for Human Detection. IEEE Computer Society Conference on Computer Vision & Pattern Recognition. DOI= https://doi.org/ 10.1109/CVPR.2005.177.Google Scholar
- Ojala, T., Pietikäinen, M., and Mäenpää, T. 2002. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis & Machine Intelligence, (7), 971--987. DOI= https://doi.org/10.1109/tpami.2002.1017623.Google Scholar
- Lowe, D. G. 2004. Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2), 91--110. DOI= https://doi.org/10.1023/b:visi.0000029664.99615.94.Google Scholar
- Iranmehr, A., Masnadi-Shirazi, H., and Vasconcelos, N. 2019. Cost-sensitive support vector machines. Neurocomputing, 343, 50--64. DOI= https://doi.org/10.1016/j.neucom.2018.11.099.Google ScholarDigital Library
- He, K., Gkioxari, G., Dollár, P., and Girshick, R. 2017. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 2961--2969). DOI= https://doi.org/10.1109/TPAMI.2018.2844175.Google Scholar
Index Terms
- Automated Detection of Sewer Pipe Defects Based on Cost-Sensitive Convolutional Neural Network
Recommendations
Cost-Sensitive Boosting
A novel framework is proposed for the design of cost-sensitive boosting algorithms. The framework is based on the identification of two necessary conditions for optimal cost-sensitive learning that 1) expected losses must be minimized by optimal cost-...
Cost-Sensitive back-propagation neural networks with binarization techniques in addressing multi-class problems and non-competent classifiers
A novel method based on cost-sensitive neural networks with binarization techniques for multi-class problems is developed.The effect of aggregation methods for the proposed method is studied.The positive synergy between the management of non-competent ...
Cost-sensitive matrixized classification learning with information entropy
AbstractClassifier design is one of the most significant fields in pattern recognition. Most classifiers are measured by classification accuracy, which assumes that all the misclassification cost are the same. In the real world, different ...
Highlights- The CsMatMHKS combine the matrixized learning framework with cost-sensitive learning.
Comments