Artificial Intelligence Review

, Volume 42, Issue 3, pp 403–425 | Cite as

Buried pipe localization using an iterative geometric clustering on GPR data

  • Ruth Janning
  • Andre Busche
  • Tomáš Horváth
  • Lars Schmidt-Thieme
Article

Abstract

Ground penetrating radar is a non-destructive method to scan the shallow subsurface for detecting buried objects like pipes, cables, ducts and sewers. Such buried objects cause hyperbola shaped reflections in the radargram images achieved by GPR. Originally, those radargram images were interpreted manually by human experts in an expensive and time consuming process. For an acceleration of this process an automatization of the radargram interpretation is desirable. In this paper an efficient approach for hyperbola recognition and pipe localization in radargrams is presented. The core of our approach is an iterative directed shape-based clustering algorithm combined with a sweep line algorithm using geometrical background knowledge. Different to recent state of the art methods, our algorithm is able to ignore background noise and to recognize multiple intersecting or nearby hyperbolas in radargram images without prior knowledge about the number of hyperbolas or buried pipes. The whole approach is able to deliver pipe position estimates with an error of only a few millimeters, as shown in the experiments with two different data sets.

Keywords

Ground penetrating radar (GPR) Object detection Hyperbola recognition Clustering Sweep line algorithm 

References

  1. Abubakar A, van den Berg PM (2002) The contrast source inversion method for location and shape reconstructions. Inverse Prob 18(2)Google Scholar
  2. Ahn SJ, Rauh W, Warnecke HW (2001) Least-squares orthogonal distances fitting of circle, sphere, ellipse, hyperbola, and parabola. Pattern Recognit 34(12):2283–2303CrossRefMATHGoogle Scholar
  3. Al-Nuaimy W, Huang Y, Nakhkash M, Fang MTC, Nguyen VT, Eriksen A (2000) Automatic detection of buried utilities and solid objects with GPR using neural networks and pattern recognition. J Appl Geophys 43:157–165CrossRefGoogle Scholar
  4. Barinova O, Lempitsky V, Kohli P (2010) On the detection of multiple object instances using hough transforms. In: IEEE conference on CVPRGoogle Scholar
  5. Birkenfeld S (2010) Automatic detection of reflexion hyperbolas in GPR data with neural networks. In: World automation congress (WAC), pp 1–6Google Scholar
  6. Boissonnat JD, Yvinec M (1998) Algorithmic geometry. Cambridge University Press, CambridgeCrossRefMATHGoogle Scholar
  7. Busche A, Janning R, Horvath T, Schmidt-Thieme L (2012) Some improvements for multi-hyperbola detection on GPR Data. In: Workshop on KDML at LWAGoogle Scholar
  8. Capineri L, Grande P, Temple JAG (1998) Advanced image-processing technique for real-time interpretation of ground-penetrating radar images. Int J Imaging Syst Technol 9:51–59CrossRefGoogle Scholar
  9. Chen H, Cohn AG (2010a) Probabilistic conic mixture model and its applications to mining spatial ground penetrating radar data. In: Workshops in SIAM conference on data mining (SDM10)Google Scholar
  10. Chen H, Cohn AG (2010b) Probabilistic robust hyperbola mixture model for interpreting ground penetrating radar data. In: Proceedings of the 2010 IEEE world congress on computational intelligence (WCCI’10), BarcelonaGoogle Scholar
  11. Cui Y, Wang L, Xiao J (2010) Automatic feature recognition for gpr image processing. World Acad Sci Eng Technol 61:176–179Google Scholar
  12. Dos Santos VRN, Porsani JL, Hirata NST (2010) Automatic classification of metallic targets using pattern recognition of GPR reflection: a study in the IAG-USP Test Site, Sao Paulo (Brazil). In: Proceedings of the 13th international conference on ground penetrating radar (GPR), pp 322–325Google Scholar
  13. Ester M, Kriegel H, Sander J, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the second international conference on knowledge discovery and data mining (KDD-96)Google Scholar
  14. Giannopoulos A (2005) Modelling ground penetrating radar by GprMax. Constr Build Mater 19(10):755–762CrossRefGoogle Scholar
  15. Janning R, Horváth T, Busche A, Schmidt-Thieme L (2012a) GamRec: a clustering method using geometrical background knowledge for GPR data preprocessing. In: Artificial intelligence applications and innovations (IFIP advances in information and communication technology 381). Springer, Heidelberg, pp 347–356Google Scholar
  16. Janning R, Horváth T, Busche A, Schmidt-Thieme L (2012b) Pipe localization by apex detection. In: Proceedings of the IET international conference on radar systems (Radar 2012). Glasgow, ScotlandGoogle Scholar
  17. Naser M, Junge A (2010) Influence of pipe filling, geometry and antenna polarisation on GPR measurements. In: Proceedings of the 13th international conference on ground penetrating radar (GPR), pp 1–6Google Scholar
  18. O’Leary P, Zsombor-Murray PZ (2004) Direct and specific least-square fitting of hyperbolæ and ellipses. Journal of Electronic Imaging 13:492–503Google Scholar
  19. Pasolli E, Melgani F, Donelli M (2009) Automatic analysis of GPR images: a pattern-recognition approach. IEEE Trans Geosci Remote Sens 47(7):2206–2217CrossRefGoogle Scholar
  20. Ristic AV, Petrovacki D, Govedarica M (2009) A new method to simultaneously estimate the radius of a cylindrical object and the wave propagation velocity from GPR data. Comput Geosci 35:1620–1630CrossRefGoogle Scholar
  21. Shao W, Bouzerdoum A, Phung SL, Su L, Indraratna B, Rujikiatkamjorn C (2010) Automatic classification of GPR signals. In: Proceedings of the 13th international conference on ground penetrating radar (GPR), pp 738–743Google Scholar
  22. Shihab S, Al-Nuaimy W (2005) Radius estimation for cylindrical objects detected by ground penetrating radar. Sens Imaging Int J 6:151–166Google Scholar
  23. Simi A, Bracciali S, Manacorda G (2008) Hough transform based automatic pipe detection for array GPR: algorithm development and on-site tests. In: Radar conference RADAR ’08. RomeGoogle Scholar
  24. Sugihartono NRH, Suksmono AB (2009) Interpretation target pattern of a buried basic object on surface ground penetrating radar system. Int J Electr Eng Inform 1:496–505Google Scholar
  25. Windsor CG, Falorni P, Capineri L (2004) Classification of buried objects from series of aligned hyperbolic arcs or ”pendants” in radar scans: estimating a buried pipe diameter. In: Progress in electromagnetics research symposium, Pisa, Italy, pp 607–610Google Scholar
  26. Windsor CG, Capineri L, Falorni P (2005) The estimation of buried pipe diameters by generalized hough transform of radar data. In: Progress in electromagnetics research symposium. Hangzhou, China, pp 345–349Google Scholar
  27. Yaman F (2009) Location and shape reconstructions of sound-soft obstacles buried in penetrable cylinders. Inverse Prob 25(6)Google Scholar
  28. Yu J, Kulkarni SR, Poor HV (2012) Robust ellipse and spheroid fitting. Pattern Recognit Lett 33(5):492–499CrossRefGoogle Scholar
  29. Zhao Y, Wu J, Xie X, Chen J, Ge S (2010) Multiple suppression in GPR image for testing back-filled grouting within shield tunnel. In: Proceedings of the 13th international conference on ground penetrating radar (GPR), pp 271–276Google Scholar
  30. Zalik KR, Zalik B (2009) A sweep-line algorithm for spatial clustering. Adv Eng Softw 40:445–451CrossRefMATHGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2013

Authors and Affiliations

  • Ruth Janning
    • 1
  • Andre Busche
    • 1
  • Tomáš Horváth
    • 2
  • Lars Schmidt-Thieme
    • 1
  1. 1.Information Systems and Machine Learning LabUniversity of HildesheimHildesheimGermany
  2. 2.Faculty of Science, Institute of Computer SciencePavol Jozef Šafárik University in KošiceKosiceSlovakia

Personalised recommendations