Improvement of the accuracy of determining movement parameters of cuts on classification humps by methods of video analysis

Authors

  • Sergey Panchenko Ukrainian State University of Railway Transport Feyerbakh sq., 7, Kharkiv, Ukraine, 61050, Ukraine
  • Ivan Siroklyn Ukrainian State University of Railway Transport Feyerbakh sq., 7, Kharkiv, Ukraine, 61050, Ukraine
  • Anton Lapko Ukrainian State University of Railway Transport Feyerbakh sq., 7, Kharkiv, Ukraine, 61050, Ukraine
  • Alexandr Kameniev Ukrainian State University of Railway Transport Feyerbakh sq., 7, Kharkiv, Ukraine, 61050, Ukraine
  • Sergii Zmii Ukrainian State University of Railway Transport Feyerbakh sq., 7, Kharkiv, Ukraine, 61050, Ukraine

DOI:

https://doi.org/10.15587/1729-4061.2016.76103

Keywords:

video analysis, optical flow, background subtraction, monitoring the parameters of cuts’ movement, classification hump

Abstract

The study proves that it is necessity to develop and specify the procedures of using a synthesis of the methods of optical flow and background subtraction in the case of controlling objects of complex shapes on a changing background and in the presence of small moving objects that are not subject to tracking. Research in this area can yield significant results to automate the movement parameters control over objects such as railway transport.

For the described conditions of practical use, it is most of all advisable to synthesize the classical Lucas-Kanade method of optical flow and the Horn-Schunck method for segmenting the frames and identifying control zones. The study describes the procedures of choosing the size of control zones and analysing a joint movement in these areas, which makes it possible to identify the movement of a cut even if the cut has been formed from different categories of wagons.

The suggested algorithms were tested on the classification hump at Odesa – the Classifying Section station (Ukraine). The obtained quantitative characteristics of the accuracy of recognizing cuts show that the conditional probability of correct work of the suggested approach is 0.8332, compared with 0.44 in the case of the classical Horn-Schunck method under the same conditions.

Author Biographies

Sergey Panchenko, Ukrainian State University of Railway Transport Feyerbakh sq., 7, Kharkiv, Ukraine, 61050

Doctor of Technical Sciences, Professor, Rector

Department of automatic and of computer remove control of train traffic

Ivan Siroklyn, Ukrainian State University of Railway Transport Feyerbakh sq., 7, Kharkiv, Ukraine, 61050

PhD, Associate Professor

Department of automatic and of computer remove control of train traffic

Anton Lapko, Ukrainian State University of Railway Transport Feyerbakh sq., 7, Kharkiv, Ukraine, 61050

PhD

Department of automatic and of computer remove control of train traffic

Alexandr Kameniev, Ukrainian State University of Railway Transport Feyerbakh sq., 7, Kharkiv, Ukraine, 61050

PhD, Associate Professor

Department of automatic and of computer remove control of train traffic

Sergii Zmii, Ukrainian State University of Railway Transport Feyerbakh sq., 7, Kharkiv, Ukraine, 61050

PhD, Associate Professor

Department of automatic and of computer remove control of train traffic

References

  1. Seroklin, I. M., Fomina, V., Brazhnik, A. (2015). Use of video image analysis methods for detaching control on hump yards. Part 1. ScienceRise, 1/2(6), 16–21. doi: 10.15587/2313-8416.2015.35869
  2. Ivanov, Y. A. (2011). Tekhnolohyy kompiuternoho zrenyia v systemakh avtovedenyia. Avtomatyka, sviaz, ynformatyka, 6, 46–48.
  3. Gasimov, R. Ch. (2011). Programnyy kompleks dlya videomonitoringa zheleznodorozhnogo pereezda. Nauchnaya sessiya GUAP. Sbornik dokladov. Part 2. Tekhnicheskie nauki, 10–12.
  4. Ivanov, Yu. A. (2011). Tekhnologii komp'yuternogo zreniya dlya nablyudeniya za ob''ektami putevoy infrastrkutury. Prom. transp. KhKhI, 5-6, 35–38.
  5. Rodrigues, T. M. (2011). A novel approach to rail crossing protection using computer vision and radio communications. Graph. And Vision, 20 (1), 41–71.
  6. Ivanov, Yu. A. (2012). Tekhnologii komp'yuternogo zreniya. Zheleznodorozhnyy transport, 12, 49
  7. Dufour, J.-Y. (2013). Intelligent video surveillance systems. Printed and bound in Great Britain by CPI Group (UK) Ltd., Croydon, Surrey CR0 4YY, 322.
  8. Chamasemani, F. F., Affendey, L. S. (2013). Systematic Review and Classification on Video Surveillance Systems. Information Technology and Computer Science, 5 (7), 87–102. doi: 10.5815/ijitcs.2013.07.11
  9. Sun, D., Roth, S., Black, M. J. (2010). Secrets of optical flow estimation and their principles. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. doi: 10.1109/cvpr.2010.5539939
  10. Bruhn, A., Weickert, J., Schnörr, C. (2005). Lucas/Kanade Meets Horn/Schunck: Combining Local and Global Optic Flow Methods. International Journal of Computer Vision, 61 (3), 1–21. doi: 10.1023/b:visi.0000045324.43199.43
  11. Baker, S., Scharstein, D., Lewis, J. P., Roth, S., Black, M. J., Szeliski, R. (2010). A Database and Evaluation Methodology for Optical Flow. International Journal of Computer Vision, 92 (1), 1–31. doi: 10.1007/s11263-010-0390-2
  12. Shapiro, L. M., Stockman, J. P. (2006). Computer Vision. Knowledge Laboratory, 2, 752.
  13. Nagy, A. T., Vamossy, Z. M. (2007). Super-Resolution for Traditional and Omnidirectional Image Sequences. John von Neumann Faculty of Informatics. Institute of Software Technology, 117–129.
  14. Siroklyn, I. M. (2012). Application of the method of the optical flow analysis to control the parameters of passenger traffic. Eastern-European Journal of Enterprise Technologies, 6/3(60), 33–36. Available at: http://journals.uran.ua/eejet/article/view/5507/4949
  15. Siroklyn, I. M. (2012). Aprobatsiya metodu avtomatychnoho kontrolyu pasazhyropotoku z vykorystannyam tekhnichnoho zoru. Informatsiyno-keruyuchi systemy na zaliznychnomu transporti: naukovo-tekhnichnyy zhurnal, 6, 22–25.

Downloads

Published

2016-08-31

How to Cite

Panchenko, S., Siroklyn, I., Lapko, A., Kameniev, A., & Zmii, S. (2016). Improvement of the accuracy of determining movement parameters of cuts on classification humps by methods of video analysis. Eastern-European Journal of Enterprise Technologies, 4(3(82), 25–30. https://doi.org/10.15587/1729-4061.2016.76103

Issue

Section

Control processes