Skip to main content

Classification of defects with ensemble methods in the automated visual inspection of sewer pipes

Pattern Analysis and Applications volume 18, pages 263–276 (2015)Cite this article

Abstract

Side scanning evaluation technology (SSET) is a visual inspection technique for sewer pipelines. It provides both frontal and 360 degree images of the interior surface of the pipe wall. Image-based pipe defect classification has been widely used for rating sewage structural conditions. The classification of defects in sewer pipe is of vital importance for maintaining the sewerage systems. Usually, a human operator identifies the defect types from the acquired images. However, the diagnosis can be easily influenced by the subjective human factors. To overcome such limitations, a reliable automated sewer pipe defect classification is highly desirable. In this paper, a sewer pipe defect classification based on ensemble methods is proposed. Due to the natural shape irregularities of pipe defects and the complexity of imaging environments, pipe defect images are highly variable. A feature extraction procedure consisting of contourlet transform and the maximum response filter bank is implemented in the proposed method. A feature vector is generated with the statistical features derived from the outputs of contourlet transform and maximum response filter bank. Four ensemble classifiers are trained to classify the feature vector to assign a defect type to the input pipe image. The best ensemble method, namely RobBoot, achieves the highest classification rates in the experiments with 239 pipe images obtained by the SSET inspection. The effectiveness and performance of the proposed method are demonstrated by comparing with other state-of-the-art techniques.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

USD 39.95

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

References

  1. Yang M-D, Su T-C (2008) Automated diagnosis of sewer pipe defects based on machine learning approaches. Expert Syst Appl 35:1327–1337

    Article  Google Scholar 

  2. Liu Z, Kleiner Y, Rajjani B, Wang L, Condit W Condition assessment of water transmission and distribution systems. United States Environmental Protection Agency, National Risk Management Research Laboratory, Ottawa, Ontario, Canada, Tech. Rep. EPA/600/R-12/017, March 2012, institute for Research in Construction, National Research Council Canada

  3. Iyer S, Sinha SK (2005) A robust approach for automatic detection and segmentation of cracks in underground pipeline images. Image Vis Comput 23:921–933

    Article  Google Scholar 

  4. Iyer S, Sinha SK (2006) Segmentation of pipe images for crack detection in buried sewers. Comput Aided Civil Infrastruct Eng 21:395–410

    Article  Google Scholar 

  5. Sinha SK, Karray F (2002) Classification of underground pipe scanned images using feature extraction and neuro-fuzzy algorithm. IEEE Trans Neural Netw 13:393–401

    Article  Google Scholar 

  6. Sinha SK, Fieguth PW (2006) Automated detection of cracks in buried concrete pipe images. Autom Constr 15:58–72

    Article  Google Scholar 

  7. Sinha SK, Fieguth PW (2006) Segmentation of buried concrete pipe images. Autom Constr 15:47–57

    Article  Google Scholar 

  8. Sinha SK, Fieguth PW (2006) Neuro-fuzzy network for the classification of buried pipe defects. Autom Constr 15:73–83

    Article  Google Scholar 

  9. Liu W, Tao D (2013) Multiview Hessian regularization for image annotation. IEEE Trans Image Process 22(7):2676–2687

    Article  MathSciNet  Google Scholar 

  10. Geng B, Tao D, Xu C, Yang L, Hua X-S (2012) Ensemble manifold regularization. IEEE Trans Pattern Anal Mach Intell 34(6):1227–1233

    Article  Google Scholar 

  11. Jiang G, Yu M, Yi W, Li F, Kim Y-D (2006) A new denoising method with contourlet transform. Lect Notes Control Inf Sci 345:626–630

    Article  Google Scholar 

  12. Do MN, Vetterli M (2005) The contourlet transform: an efficient directional multiresolution image representation. IEEE Trans Image Process 14(12):2091–2106

    Article  MathSciNet  Google Scholar 

  13. Wu W, Liu Z, Gueaieb W, He X (2011) Single-image super-resolution based on markov random field and contourlet transform. J Electron Imaging 20:023005

    Article  Google Scholar 

  14. Varma M, Zisserman A (2005) A statistical approach to texture classification from single images. Int J Comput Vis 62(1–2):61–81

    Article  Google Scholar 

  15. Guo Z, Zhang L, Zhang D (2009) Rotation invariant texture classification using binary filter response pattern (BFRP). In: Jiang X, Petkov N (eds) Proceedings of 13th international conference on computer analysis of images and patternsLNCS 5702, Munster, Germany, pp 1130–1137

  16. Schmid C (2001) Constructing models for content-based image retrieval. In: IEEE conference on computer vision and pattern recognition, vol 2, pp 39–45

  17. Leung T, Malik J (2001) Representing and recognizing the visual appearance of materials using three-dimensional textons. Int J Comput Vis 43:29–44

    Article  MATH  Google Scholar 

  18. Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 6:610–621

    Article  Google Scholar 

  19. Tamura H, Mori S, Yamawaki T (1978) Textural features corresponding to visual perception. IEEE Trans Syst Man Cybern 8:460–472

    Article  Google Scholar 

  20. NIST/SEMATECH (2011) e-handbook of statistical methods. National Institute of Standards and Technology http://www.itl.nist.gov/div898/handbook/

  21. Bock KWD, den Poel DV (2011) An empirical evaluation of rotation-based ensemble classifiers for customer churn prediction. Expert Syst Appl 38(10)

  22. Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139

    Article  MATH  MathSciNet  Google Scholar 

  23. Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. In: Proceedings of the ninth annual conference on computational learning theory, pp 325–332

  24. Theodoridis S, Koutroumbas K (2006) Pattern recognition, 3rd edn. Elsevier, Amsterdam

  25. Zhang C-X, Zhang J-S (2008) Rotboost: a technique for combining rotation forest and adaboost. Pattern Recogn Lett 29:1524–1536

    Article  Google Scholar 

  26. Prasad AM, Iversion LR, Liaw A (2006) Newer classification and regression tree techniques: Bagging and randomforestfor ecological prediction. Ecosystems 9:181–199

    Article  Google Scholar 

  27. Svetnik V, Liaw A, Tong C, Culberson JC (2003) Random forest: A classification and regression tool for compound classificationand QSAR modeling. J Chem Inf Comput Sci 43(6):1947–1958

    Article  Google Scholar 

  28. Gislason PO, Benediktsson JA, Sveinsson JR (2006) Random forests for land cover classification. Pattern Recogn Lett 27:294–300

    Article  Google Scholar 

  29. Svetnik V, Liaw A, Tong C, Wang T (2004) Multiple classifier systems. Application of Breiman’s random forest to modeling structure-activity relationships of pharmaceutical molecules. In: Lecture notes in computer science, vol 3077. Springer, Berlin

  30. Breiman L (2001) Random forests. Mach Learn 45(1):5–32

    Article  MATH  Google Scholar 

  31. Breiman L (2001) Random forests. University of California, Berkeley, CA 94720, Technical Report

  32. Rodriguez JJ, Kuncheva LI (2006) Rotation forest: a new classifier ensemble method. IEEE Trans Pattern Anal Mach Intell 28(10):1619–1630

    Article  Google Scholar 

  33. Kuncheva LI, Rodriguez JJ (2007) An experimental study on rotation forest ensembles. In: Lecture notes in computer science, vol 4472. Springer, Berlin, pp 459–468

  34. Kotsiantis S (2011) Combining bagging, boosting, rotation forest and random subspace methods. Artif Intell Revi 35(3):223–240

    Article  Google Scholar 

  35. Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotatio invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971–987

    Article  Google Scholar 

  36. Zhang L, Zhang L, Guo Z, Zhang D (2010) Monogenic-lbp: a new approach for rotation invariant texture classification. In: IEEE international conference on image processing, Hong Kong, China, pp 2677–2680

  37. Guo Z, Zhang L, Zhang D, Zhang S (2010) rotation invariant texture classification using adaptive LBP with directional statistical features. In: IEEE international conference on image processing, Hong Kong, China, pp 285–288

Download references

Acknowledgments

Hydromax (http://www.hydromaxusa.com) is acknowledged for providing the inspection data used for this study. We are also grateful to Dr. Chunxia Zhang for her helpful discussion and Matlab implementation of Rotboost algorithm. This work is supported by National Research Council Canada and partly supported by National Natural Science Foundation of China (No.61271330).

Author information

Authors and Affiliations

  1. Sichuan University, Chengdu, 610064, China

    Wei Wu & Yan He

  2. Toyota Technological Institute/University of Ottawa, 2-12-1 Hisakata, Tenpaku-Ku, Nagoya, Aichi, 468-8511, Japan

    Zheng Liu

Authors
  1. Wei Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zheng Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yan He
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zheng Liu.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Wu, W., Liu, Z. & He, Y. Classification of defects with ensemble methods in the automated visual inspection of sewer pipes. Pattern Anal Applic 18, 263–276 (2015). https://doi.org/10.1007/s10044-013-0355-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-013-0355-5

Keywords

  • Pipe condition assessment
  • Machine vision
  • Contourlet transform
  • Maximum response filter bank
  • Ensemble classification