Journal of the Korean Society for Railway (한국철도학회논문집)

The Korean Society for Railway (한국철도학회)
권호 표지
DOI QR코드

DOI QR Code

Development of Automatic Crack Identification Algorithm for a Concrete Sleeper Using Pattern Recognition

패턴인식을 이용한 콘크리트침목의 자동균열검출 알고리즘 개발

  • Kim, Minseu (Institute of Railroad Convergence Technology, Korea National University of Transportation) ;
  • Kim, Kyungho (A BEST Co. Ltd.) ;
  • Choi, Sanghyun (Department of Railroad Facility Engineering, Korea National University of Transportation)
  • Received : 2017.02.10
  • Accepted : 2017.05.25
  • Published : 2017.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Concrete sleepers, installed on majority of railroad track in this nation can, if not maintained properly, threaten the safety of running trains. In this paper, an algorithm for automatically identifying cracks in a sleeper image, taken by high-resolution camera, is developed based on Adaboost, known as the strongest adaptive algorithm and most actively utilized algorithm of current days. The developed algorithm is trained using crack characteristics drawn from the analysis results of crack and non-crack images of field-installed sleepers. The applicability of the developed algorithm is verified using 48 images utilized in the training process and 11 images not used in the process. The verification results show that cracks in all the sleeper images can be successfully identified with an identification rate greater than 90%, and that the developed automatic crack identification algorithm therefore has sufficient applicability.

국내 대부분의 선구에 부설된 콘크리트침목은 적절히 유지관리되지 않을 경우 열차 운행의 안전성을 심각하게 위협하는 요소가 될 수 있다. 이 연구에서는 최근 가장 강력한 적응성(adaptive)을 갖는 기법으로 활용 범위를 넓히고 있는 Adaboost를 이용하여 고해상도카메라로 촬영한 침목이미지에서 균열을 자동검출할 수 있는 알고리즘을 개발하였다. 개발된 알고리즘은 실제 침목에 발생한 균열 및 비균열 이미지를 분석한 후 도출한 균열특징을 이용하여 학습하였다. 침목균열 자동검출 알고리즘의 적용성은 48개의 학습이미지와 11개의 비학습이미지를 이용하여 검토하였다. 검토 결과 학습이미지와 비학습이미지 모두 균열폭과 균열길이에 대한 인식률이 90% 이상으로 나타났으며, 충분한 균열인식 성능을 갖는 것으로 나타났다.

Keywords

References

  1. M.S. Kaseko, Z. Lo, S. Ritchie (1994) Comparison of traditional and neural classifiers for pavement-crack detection, Journal of Transportation Engineering, 120(4), pp. 552-569. https://doi.org/10.1061/(ASCE)0733-947X(1994)120:4(552)
  2. Y. Wang (1998) Neural network approach to image reconstruction from projections, International Journal of Imaging Systems and Technology, 9(5), pp. 381-387. https://doi.org/10.1002/(SICI)1098-1098(1998)9:5<381::AID-IMA8>3.0.CO;2-6
  3. W. Benning, J. Lange, R. Schwermann, C. Effkemann, S. Gortz (2004) Monitoring crack origin and evolution at concrete elements using photogrammetry, International Archives of Photogrammetry Remote Sensing and Spatial Information Sciences, 35(5), pp. 678-683.
  4. I. Giakoumis, N. Nikolaidis, I. Pitas (2006) Digital image processing techniques for the detection and removal of cracks in digitized paintings, IEEE Transactions on Image Processing, 15(1), pp. 178-188. https://doi.org/10.1109/TIP.2005.860311
  5. J. Ando, T. Nagao (2009) Automatic construction of accurate image processing using Adaboost, Fifth International Workshop on Computational Intelligence and Applications, Hiroshima University, Japan, pp. 296-301.
  6. A. Marques (2012) Automatic Road Pavement Crack Detection Using SVM, Thesis, Instituto Superior Tecnico, Lisbon, Portugal.
  7. B. Lee (2003) Development of Detecting System for Concrete Surface Cracks Using Image Processing and Artificial Neural Network, Thesis, Korea Advanced Institute of Science and Technology.
  8. B. Lee, J. Shin, C. Park (2008) Development of image processing program to inspect concrete bridges, Proceedings of 2008 Spring Annual Conference, Korea Concrete Institute, Yong Pyong, Korea, 20(1), pp. 189-192.
  9. C.-H. Choo, S.-W. Park, H.-T. Kim, K.-H. Jee, T.-G. Yoon (2011) Analysis and cause of occurrence of lining cracks on NATM tunnel based on the precise inspection for safety and diagnosis - Part I, Journal of Tunnelling and Undergraound Space Association, 13(3), pp. 199-214.
  10. Y. Freund, R.E. Schapire (1999) A short introduction to boosting, Journal of Japanese Society for Artificial Intelligence, 14(5), pp. 771-780.
  11. H. Han (2009) Introduction to Pattern Recognition, Hanbit Media, Seoul, Korea, pp. 514-523.
  12. R. Schapire, Y. Singer (1999) Improved boosting algorithms using confidence-rated predictions, Machine Learning, 37(3), pp. 297-335. https://doi.org/10.1023/A:1007614523901
  13. K. Lee (2008) An Implementation for the Face Recognition Visual Monitoring System Using Adaboost and PCA Algorithm, Thesis, Ajou University.