Reliability of Manual Assessments in Determining the Types of Vegetation on Railway Tracks

  • Siril YellaEmail author
  • Roger G. Nyberg
  • Narendra K. Gupta
  • Mark Dougherty
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9419)


Current day vegetation assessments within railway maintenance are (to a large extent) carried out manually. This study has investigated the reliability of such manual assessments by taking three non-domain experts into account. Thirty-five track images under different conditions were acquired for the purpose. For each image, the raters’ were asked to estimate the cover of woody plants, herbs and grass separately (in %) using methods such as aerial canopy cover, aerial foliar cover and sub-plot frequency. Visual estimates of raters’ were recorded and analysis-of-variance tests on the mean cover estimates were investigated to see whether if there were disagreements between the raters’. Intra-correlation coefficient was used to study the differences between the estimates. Results achieved in this work revealed that seven out of the nine analysis-of-variance tests conducted in this study have demonstrated significant difference in the mean estimates of cover (p < 0.05).


Woody Plant Academic Staff Visual Estimate Railway Track Vertical Projection 
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.


  1. 1.
    Hulin, B., Schussler, S.: Measuring vegetation along railway tracks. In: Proceedings of the IEEE Intelligent Transportation Systems Conference, pp. 561–565 (2005)Google Scholar
  2. 2.
    Banverket: Vegetation maintenance manual, Bvh 827.1, Original title in Swedish: Handbok om vegetation’ (2000)Google Scholar
  3. 3.
    Banverket: Vegetation maintenance requirements, Bvh 827.2, Original title in Swedish: behovsanalys infor vegetationsreglering’ (2001)Google Scholar
  4. 4.
    Banverket: Safety inspections manual, Bvf 807.2, Original title in Swedish: sakerhetsbesiktning av fasta anlaggningar (2005)Google Scholar
  5. 5.
    Nyberg, R.G., Yella, S., Gupta, N., Dougherty, M.: Inter-rater reliability in determining types of vegetation on railway track beds. In: Accepted for Publication in the 3rd International Workshop on Data Quality and Trust in Big Data in Conjunction with the 16th International Conference on Web Information Systems Engineering (WISE), Miami, USA (2015)Google Scholar
  6. 6.
    Yella, S., Nyberg, R.G., Payvar, B., Dougherty, M., Gupta, N.: Machine vision approach for automating vegetation detection on railway tracks. J. Intell. Syst. 22(2) (2013). ISSN 2191-026XGoogle Scholar
  7. 7.
    Nyberg, R.G., Gupta, N., Yella, S. Dougherty, M.: Detecting plants on railway embankments. J. Softw. Eng. Appl. 6(3B), pp. 8–12 (2013) ISSN online 1945-3124Google Scholar
  8. 8.
    Nyberg, R.G., Gupta, N., Yella, S. Dougherty, M.: Monitoring vegetation on railway embankments: supporting maintenance decisions. In: Proceedings of the 2013 International Conference on Ecology and Transportation, Scottsdale, Arizona, USA (2013)Google Scholar
  9. 9.
    Coulloudon, B., Eshelman, K., Gianola, J., Nea, H.: Sampling vegetation attributes, Interagency Technical Reference BLM/RS/ST- 96/002 + 1730, Bureau of Land Management’s National Applied Resource Sciences Center, Bureau of Land management. National Business Center. BC-650B. P.O. Box 25047, Denver, Colorado 80225-0047 (1999)Google Scholar
  10. 10.
    Shrout, P., Fleiss, J.: Intraclass correlations: Uses in assessing rater reliability. Psychol. Bull. 86, 420–428 (1979)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Siril Yella
    • 1
    Email author
  • Roger G. Nyberg
    • 1
    • 2
  • Narendra K. Gupta
    • 2
  • Mark Dougherty
    • 1
  1. 1.Department of Computer EngineeringDalarna UniversityBorlängeSweden
  2. 2.School of Engineering and Built EnvironmentEdinburgh Napier UniversityEdinburghUK

Personalised recommendations