Application of wavelet transform into precise localization of railway rail edges in visual diagnostic of track

Piotr Bojarczak

doi:10.2478/v10174-012-0001-9

Authors

Piotr Bojarczak Technical University of Radom, Malczewskiego 29, 26-600 Radom, Poland Author

DOI:

https://doi.org/10.2478/v10174-012-0001-9

Keywords:

wavelet transform, diagnostic of trock

Abstract

The paper presents the application of wavelet transform into precise localization of railway rail edges. The precise localization of inner edges of the rail is particularly crucial in detection of surface flaws by the vision system. The proposed method uses the multi-resolution analysis in detection of rail edges. Application of the wavelet transform and the choice of the right combination of decomposition levels along with wavelet type immunizes the proposed algorithm against the variation of luminance of analyzing image. The algorithm is additionally resistant to shadows incidentally appearing in analyzing images. The performance of algorithm has been tested on the images coming from real vision system installed on the carriage.

References

Babenko P.: Visual inspection of railroad tracks, Doctoral Thesis, University of Central Florida, Orlando, 2009.

Bevington P. R., Robinson D. K.: Data Reduction and Error Analysis for the Physical Sciences, 2nd Ed., WCB/McGraw-Hill, Boston, 1992.

Bojarczak P., Lesiak P.: Zastosowanie hybrydowej sieci neuronowej do klasyfikacji drewnianych podkładów kolejowych, Prace Naukowe, Transport, Politechnika Warszawska z.78, 2011.

Bojarczak P., Lesiak P.: Visual system diagnosing the state of elements fastening the rail to the sleepers, Pomiary, Automatyka, Kontrola, 12/ 2011.

Bovik A.: Handbook of Image and Video Processing, Academic Press, 2000.

Daubechies I.: Ten lectures on wavelets, SIAM Press, 1988.

Draper N. R., Smith H.: Applied Regression Analysis, 3rd Ed., John Wiley & Sons, New York, 1998.

Kedra Z.: Diagnostyka obrazowa rozjazdów kolejowych, Logistyka 6/2011(CD).

Khandogin I., Kummert A., Maiwald D.: Nonlinear image processing for automatic inspection of railroad lines, IEEE Workshop on Nonlinear Signal and Image Processing, Michigan, USA, 1997.

Lesiak P.: Diagnostic technology of contact-stress flaws such as head checking in railway rails, Monograph No 121,Technical University of Radom, 2008.

Lesiak P., Bojarczak P.: Application of Wavelets and Fuzzy sets to detection of head checking defects in railway rail, Transport Systems Telematics , 10th Conference TST 2010, Communications in Computer and Information Science 104, Springer 2010.

Lin Jie, Luo Siwei, Li Qingyong, Zhang Hanqing, Ren Shengwei.: Real-time Rail head surface defect detection: a geometrical approach, IEEE International Symposium on Industrial Electronics, Seoul, Korea, 2009.

Mallat S.: A theory for multiresolution signal decomposition: the wavelet representation, IEEE Trans. PAMI, vol. 11, 1989.