Inspection of physical surface defects is a significant concern in many industrial areas. In railway systems, this process mainly includes the detection and classification of defects in rails and wheels, for which laser-based optical inspection technologies have gradually been applied in the form of 2D profile measurement, benefiting from its high precision and robustness to surface conditions. However, defect classification and evaluation after the initial detection works still rely heavily on human inspectors to make maintenance suggestions. The linear nature of rails makes it possible to increase the dimension of rail measurement data from 2D to 3D by aligning 2D profiles along the rail, from which more comprehensive diagnosis information becomes available. In combination with appropriate artificial intelligence algorithms, this approach can potentially replace human-dominated defect classification and evaluation work. This study presents a 3D model-based railway track surface defect classification and evaluation method. A set of geometrical features are extracted from the 3D model of track surface defects to describe a distinguishable pattern for each category of defect. Multi-class classifiers are then tested and have shown promising results on a group of artificial track surface defects, giving a systemic solution for 3D model-based automatic track surface defect inspection.

References

1. 1)
  - 18. Luo, Q., Fang, X., Sun, Y., et al: ‘Surface defect classification for hot-rolled steel strips by selectively dominant local binary patterns’, IEEE Access, 2019, 7, pp. 23488–23499.
2. 2)
  - 16. Şevik, U., Karakullukçu, E., Berber, T., et al: ‘Automatic classification of skin burn colour images using texture-based feature extraction’, IET Image Process., 2019, 13, (11), pp. 2018–2028.
3. 3)
  - 31. Keshet, L.: ‘Math 103’ (University of British Columbia, Canada, 2012).
4. 4)
  - 30. Davies, E.R.: ‘Computer and machine vision: theory, algorithms, practicalities’ (Academic Press, Inc., UK., 2012, 1st edn.), p. 912.
5. 5)
  - 15. Bishop, C.M.: ‘Pattern recognition and machine learning’ (Information Science and Statistics) (Springer-Verlag, USA., 2006).
6. 6)
  - 33. Hatcher, L., Stepanski, E.J.: ‘A step-by-step approach to using the SAS system for univariate and multivariate statistics’ (SAS Institute, USA., 1994), p. xiv, p. 552.
7. 7)
  - 28. Chen, K., Kvasnicka, V., Kanen, P.C., et al: ‘Supervised and unsupervised pattern recognition: feature extraction and computational intelligence [book review]’, IEEE Trans. Neural Netw., 2001, 12, (3), pp. 644–647.
8. 8)
  - 2. Cannon, D.F., Edel, K.O., Grassie, S.L., et al: ‘Rail defects: an overview’, Fatigue Fract. Eng. M., 2003, 26, (10), pp. 865–887.
9. 9)
  - 24. Zhang, G., He, J., Li, X.: ‘3D vision inspection for internal surface based on circle structured light’, Sensor. Actuat. A: Phys., 2005, 122, (1), pp. 68–75.
10. 10)
  - 11. Zou, C., He, B., Zhang, L., et al: ‘Scene flow for 3D laser scanner and camera system’, IET Image Process., 2018, 12, (4), pp. 612–618.
11. 11)
  - 26. Micro-Epsilon: ‘scanCONTROL // 2D/3D laser scanner (laser profile sensors)’ (Micro-Epsilon, Germany, 2015).
12. 12)
  - 8. Zhou, P., Xu, K., Wang, D.: ‘Rail profile measurement based on line-structured light vision’, IEEE Access, 2018, 6, pp. 16423–16431.
13. 13)
  - 3. Department of Transporation: ‘Rolling contact fatigue: a comprehensive review’ (NRC, USA., 2011), pp. 9–19.
14. 14)
  - 19. Kumar, A.: ‘Computer-vision-based fabric defect detection: a survey’, IEEE Trans. Ind. Electron., 2008, 55, (1), pp. 348–363.
15. 15)
  - 23. Wu, B., Xue, T., Zhang, T., et al: ‘A novel method for round steel measurement with a multi-line structured light vision sensor’, Meas. Sci. Technol., 2010, 21, (2), p. 025204.
16. 16)
  - 20. Trinh, H., Haas, N., Li, Y., et al: ‘Enhanced rail component detection and consolidation for rail track inspection’. 2012 IEEE Workshop on the Applications of Computer Vision (WACV), Breckenridge, CO, USA, January 2012, pp. 289–295.
17. 17)
  - 10. Hani, A.F.M., Eltegani, N.M., Arshad, L., et al: ‘Wound model reconstruction from three-dimensional skin surface imaging using the convex hull approximation method’, IET Image Process., 2012, 6, (5), pp. 521–533.
18. 18)
  - 17. Xue-Wu, Z., Yan-Qiong, D., Yan-Yun, L., et al: ‘A vision inspection system for the surface defects of strongly reflected metal based on multi-class SVM’, Expert Syst. Appl., 2011, 38, (5), pp. 5930–5939.
19. 19)
  - 1. Network Rail: ‘Inspection and maintenance of permanent way’ (NR, UK., 2018).
20. 20)
  - 22. Forest, J., Salvi, J.: ‘A review of laser scanning three-dimensional digitisers’. IEEE/RSJ Int. Conf. Intelligent Robots Systems, Lausanne, Switzerland, September–October 2002, pp. 73–78.
21. 21)
  - 29. Xie, X.: ‘A review of recent advances in surface defect detection using texture analysis techniques’, ELCVIA, 2008, 7, (3), pp. 1–22.
22. 22)
  - 5. ‘Track Measuring Systems: Full Rail Profile’, http://www.mermecgroup.com, accessed May 2019.
23. 23)
  - 27. Otsu, N.: ‘A threshold selection method from gray-level histograms’, IEEE Trans. Syst. Man Cybern., 1979, 9, (1), pp. 62–66.
24. 24)
  - 34. Kim, J., Mueller, C.W.: ‘Introduction to factor analysis: what it is and how to do it’ (Quantitative Applications in the Social Sciences) (Sage Publications, 1978), vol. 13.
25. 25)
  - 13. Wang, Y., Yang, Y., Liu, Q.: ‘Feature-aware trilateral filter with energy minimization for 3D mesh denoising’, IEEE Access, 2020, 8, pp. 52232–52244.
26. 26)
  - 21. Townes, C.H.: ‘How the laser happened: adventures of a scientist’ (Oxford University Press, UK., 1999).
27. 27)
  - 6. Rusu, M.F.: ‘Automation of railway switch and crossing inspection’. PhD thesis, University of Birmingham, 2017.
28. 28)
  - 4. Alahakoon, S., Sun, Y.Q., Spiryagin, M., et al: ‘Rail flaw detection technologies for safer, reliable transportation: a review’, J. Dyn. Sys., Meas., Control, 2017, 140, (2), p. 020801.
29. 29)
  - 7. Xiong, Z., Li, Q., Mao, Q., et al: ‘A 3D laser profiling system for rail surface defect detection’, Sens. (Basel), 2017, 17, (8), p. E1791.
30. 30)
  - 32. Berrar, D.: ‘Cross-validation’, in Ranganathan, S., et al (Eds.): ‘Encyclopedia of bioinformatics and computational biology’ (Academic Press, Netherlands, 2019), pp. 542–545.
31. 31)
  - 14. Ye, J., Stewart, E., Roberts, C.: ‘Use of a 3D model to improve the performance of laser-based railway track inspection’, Proc. IMechE, F: J. Rail Rapid Transit, 2018, 233, (3), pp. 337–355.
32. 32)
  - 9. Chondronasios, A., Popov, I., Jordanov, I.: ‘Feature selection for surface defect classification of extruded aluminum profiles’, Int. J. Adv. Manuf. Technol., 2015, 83, (1–4), pp. 33–41.
33. 33)
  - 25. Papaelias, M.P., Lugg, M.C., Roberts, C., et al: ‘High-speed inspection of rails using ACFM techniques’, NDT E Int., 2009, 42, (4), pp. 328–335.
34. 34)
  - 12. Yang, Y., Li, B., Li, P., et al: ‘A two-stage clustering based 3D visual saliency model for dynamic scenarios’, IEEE Trans. Multimedia, 2019, 21, (4), pp. 809–820.

Method for automatic railway track surface defect classification and evaluation using a laser-based 3D model

References

Related content