Structural Monitoring and Maintenance

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Multi-class support vector machines for paint condition assessment on the Sydney Harbour Bridge using hyperspectral imaging

  • Received : 2015.03.20
  • Accepted : 2015.08.09
  • Published : 2015.09.25
⟨ Previous Next ⟩

Abstract

Assessing the condition of paint on civil structures is an important but challenging and costly task, in particular when it comes to large and complex structures. Current practices of visual inspection are labour-intensive and time-consuming to perform. In addition, this task usually relies on the experience and subjective judgment of individual inspectors. In this study, hyperspectral imaging and classification techniques are proposed as a method to objectively assess the state of the paint on a civil or other structure. The ultimate objective of the work is to develop a technology that can provide precise and automatic grading of paint condition and assessment of degradation due to age or environmental factors. Towards this goal, we acquired hyperspectral images of steel surfaces located at long (mid-range) and short distances on the Sydney Harbour Bridge with an Acousto-Optics Tunable filter (AOTF) hyperspectral camera (consisting of 21 bands in the visible spectrum). We trained a multi-class Support Vector Machines (SVM) classifier to automatically assess the grading of the paint from hyperspectral signatures. Our results demonstrate that the classifier generates highly accurate assessment of the paint condition in comparison to the judgement of human experts.

Keywords

References

  1. Angelopoulou, E. (2000), "Objective colour from multispectral imaging", European Conference on Computer Vision.
  2. Angelopoulou, E., Molana, R. and Daniilidis, K. (2001), "Multispectral Skin Color Modeling", Computer Vision and Pattern Recognition, 2, 635-642.
  3. ASTM-D610-08 (2012), Standard Practice for Evaluating Degree of Rusting on Painted Steel Surfaces, ASTM International, West Conshohocken, PA.
  4. ASTM-D662-93 (2011), Standard Test Method for Evaluating Degree of Erosion of Exterior Paints, ASTM International, West Conshohocken, PA.
  5. ASTM-D5065-13 (2013), Standard Guide for Assessing the Condition of Aged Coatings on Steel Surfaces, ASTM International, West Conshohocken, PA.
  6. Australia, E.S. (2010), "Sydney Harbour Bridge", Retrieved 9th of January, 2015, from http://www.experiencesydneyaustralia.com/sydney-australia-highlights/sydney-harbour-bridge/.
  7. Bayer, G.T. and Zamanzadeh, M. (2004), "Failure analysis of paints and coatings", published internally by Matco Associates, 331.
  8. Boyd, S. and Vandenberghe, L. (2004), Convex Optimization, Cambridge University Press.
  9. Buchsbaum, G. (1980), "A spatial processor model for object colour perception", J. Franklin Inst., 310(1), 1-26. https://doi.org/10.1016/0016-0032(80)90058-7
  10. Chang, C.C. and Lin, C.J. (2011), "LIBSVM: A library for support vector machines", ACM T.Intell. Syst. Technol., 2(3), 21-27:27.
  11. Cristianini, N. and Shawe-Taylor, J. (2000), An Introduction to Support Vector Machines: And Other Kernel-based Learning Methods, Cambridge University Press, New York, NY, USA.
  12. Denes, L.J., Gottlieb, M.S. and Kaminsky, B. (1998), "Acousto-optic tunable filters in imaging applications", Opt. Eng., 37(4), 1262-1267. https://doi.org/10.1117/1.601962
  13. Dundar, M. and Landgrebe, D. (2004), "Toward an optimal supervised classifier for the analysis of hyperspectral data", IEEE T. Geosci. Remote, 42(1), 271-277. https://doi.org/10.1109/TGRS.2003.817813
  14. Finlayson, G.D. and Trezzi, E. (2004), "Shades of gray and colour constancy", Color Imaging Conference, Society for Imaging Science and Technology.
  15. Gerlock, J.L., Smith, C.A., Cooper, V.A., Dusbiber, T.G. and Weber, W.H. (1998), "On the use of Fourier transform infrared spectroscopy and ultraviolet spectroscopy to assess the weathering performance of isolated clearcoats from different chemical families", Polym. Degrad. Stabil., 62(2), 225-234. https://doi.org/10.1016/S0141-3910(97)00279-6
  16. Goetz, A.F.H. (2009), "Three decades of hyperspectral remote sensing of the Earth: A personal view", Remote Sens. Environ., 113(1), 5-16. https://doi.org/10.1016/j.rse.2007.12.014
  17. Gupta, N., Dahmani, R. and Choy, S. (2002), "Acousto-optic tunable filter based visible to near-infrared spectropolarimetric imager", Opt. Eng., 41(5), 1033-1038. https://doi.org/10.1117/1.1467936
  18. Healey, G. and Slater, D. (1999), "Invariant recognition in hyperspectral images", IEEE Conf. on Computer Vision and Pattern Recognition, 1438-1043.
  19. Huynh, C.P. and Robles-Kelly, A. (2010), "Hyperspectral imaging for skin recognition and biometrics", IEEE International Conference on Image Processing (ICIP), 2325-2328.
  20. Kimmel, R., Elad, M., Shaked, D., Keshet, R. and Sobel, I. (2003), "A variational framework for retinex", Int. J. Comput. Vision., 52(1), 7-23. https://doi.org/10.1023/A:1022314423998
  21. Land, E.H. (1986), "Recent advances in Retinex theory", Vision Res., 26(1), 7-21. https://doi.org/10.1016/0042-6989(86)90067-2
  22. Land, E.H. and McCann, J.J. (1971), "Lightness and retinex theory", J. Opt. Soc. Am., 61(1), 1-11. https://doi.org/10.1364/JOSA.61.000001
  23. McCann, J.J., Hall, J.A. and Land, E.H. (1977), "Color Mondrian experiments: the study of average spectral distributions", J. Opt. Soc. Am., 67, 1380.
  24. NSW, G. (2011a), "Sydney Harbour Bridge: Rivets", Retrieved 9th of January, 2015, from http://sydney-harbour-bridge.bos.nsw.edu.au/engineering-studies/rivets.php.
  25. NSW, G. (2011), "Sydney Harbour Bridge: Corrosion", Retrieved 9th of January, 2015, from http://sydney-harbour-bridge.bos.nsw.edu.au/engineering-studies/corrosion.php.
  26. Platt, J.C. (1999), Fast Training of Suport Vector Machines using Sequential Minimal Optimization, Advances in Kernel Methods: Support Vector Learning, Christopher J.C. Burges and A.J. Smola, Cambridge, MA, USA, MIT Press: 185-208.
  27. Poliskie, M. and Clevenger, J.O. (2008), "Fourier transform infrared (FTIR) spectroscopy for coating characterization and failure analysis", Metal Finishing, 106(5), 44-47. https://doi.org/10.1016/S0026-0576(08)80126-2
  28. Slater, D. and Healey, G. (1997), "Object recognition using invariant profiles", Proceedings of the Computer Vision and Pattern Recognition, IEEE.
  29. Suen, P.H. and Healey, G. (2001), "Invariant mixture recognition in hyperspectral images", Int. Conference on Computer Vision, IEEE.
  30. Tiong, U. and Clark, G. (2011), Aircraft Joints and Corrosion Control, ICAF 2011 Structural Integrity: Influence of Efficiency and Green Imperatives, J. Komorowski, Springer Netherlands, 625-634.
  31. Van de Weijer, J., Gevers, T. and Gijsenij, A. (2007), "Edge-based color constancy", IEEE T. Image Process., 16(9), 2207-2214. https://doi.org/10.1109/TIP.2007.901808
  32. Wyszecki, G. and Stiles, W. (2000), Color Science: Concepts and Methods, Quantitative Data and Formulae. Wiley.

Cited by

  1. Multisource Data Fusion for Classification of Surface Cracks in Steel Pipes vol.1, pp.2, 2015, https://doi.org/10.1115/1.4038862
  2. Online unsupervised detection of structural changes using train–induced dynamic responses vol.165, pp.None, 2015, https://doi.org/10.1016/j.ymssp.2021.108268