Advertisement

Recognition of Cross Profiles of Roadbed Based on Polygonal Representations

  • Andrey G. Bronevich
  • Alexander E. Lepskiy
  • Vladimir I. Umansky
  • Dmitry A. Yakushev
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8251)

Abstract

The paper is devoted to the description of two approaches for recognizing railway roadbed profiles, obtained with the help of laser scanning. The first approach is based on the identification of similar parts of comparing profiles, presented by their polygonal representations. The second approach uses weighted functional metrics, where it is possible to process incomplete data and then to make a choice on the set of preferences.

Keywords

Piecewise Linear Function Threshold Comparison Distance Image Similar Part Distance Transformation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. [1]
    Babenko, P.: Visual inspection of railroad tracks. In PhD Thesis (2009), http://server.cs.ucf.edu/vision/papers/theses/Babenko_Pavel.pdf
  2. [2]
    Berry, A., Nejikovsky, B., Gilbert, X., Jajaddini, A.: High speed video inspection of joint bars using advanced image collection and processing techniques. In: Proc. of World Congress on Railway Research (2008)Google Scholar
  3. [3]
    Borgefors, G.: Distance transformations in digital images. Computer Vision, Graphics, and Image Processing 34, 344–371 (1986)CrossRefGoogle Scholar
  4. [4]
    Bronevich, A.G., Karkishchenko, A.N., Umanskiy, V.I.: Statistical method of restoring the profile from laser scanning data. Digital Signal Processing 4, 42–49 (2011) (in Russian)Google Scholar
  5. [5]
    Bronevich, A.G., Lepskiy, A.E.: Some effective approaches to the recognition of three-dimensional images of objects by the external contour. In: Proc. of the 7th National Conf. on Artificial Intelligence, Pereslavl-Zaleski, vol. 2, pp. 557–565 (2000) (in Russian)Google Scholar
  6. [6]
    Constructional Norms and Rules 32-01-95. The railways of 1520 mm (1995) (in Russian)Google Scholar
  7. [7]
    Liu, H.C., Srinath, M.D.: Partial Shape Classification Using Contour Matching in Distance Transformation. IEEE Trans. on Pattern Anal. and Mach. Intel. 11(11), 1072–1079 (1990)CrossRefGoogle Scholar
  8. [8]
    Machine Vision Inspection of Railroad Track. Technical report, NEXTRANS Project No.0281Y02 (2011)Google Scholar
  9. [9]
    Trinh, H., Haas, N., Li, Y., Otto, C., Pankanti, S.: Enhanced Rail Component Detection and Consolidation for Rail Track Inspection. In: Proc. IEEE Workshop on the Applications of Computer Vision, pp. 289–295 (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Andrey G. Bronevich
    • 1
    • 2
  • Alexander E. Lepskiy
    • 1
  • Vladimir I. Umansky
    • 3
  • Dmitry A. Yakushev
    • 3
  1. 1.National Research University ”Higher School of Economics”MoscowRussia
  2. 2.Development and Planning Institute for Railway Information Technology, Automation and TelecommunicationJSC ResearchMoscowRussia
  3. 3.JSC IntechgeotransMoscowRussia

Personalised recommendations