Detecting Plants on Railway Embankments

Roger G. Nyberg, Narendra Gupta, Siril Yella, Mark Dougherty

Dalarna University, Department of Computer Engineering, Borlange, Sweden.
Edinburgh Napier University, School of Engineering and the Built Environment, Edinburgh, UK.

DOI: 10.4236/jsea.2013.63B003                

Abstract

This paper investigates problems concerning vegetation along railways and proposes automatic means of detecting ground vegetation. Digital images of railway embankments have been acquired and used for the purpose. The current work mainly proposes two algorithms to be able to achieve automation. Initially a vegetation detection algorithm has been investigated for the purpose of detecting vegetation. Further a rail detection algorithm that is capable of identifying the rails and eventually the valid sampling area has been investigated. Results achieved in the current work report satisfactory (qualitative) detection rates.

 

Keywords

Railway Engineering; Railway Embankments; Condition Monitoring; Image Processing; Color Segmentation; Railway Maintenance; Vegetation Detection

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	B. Hulin and S. Schussler. Measuring vegetation along railway tracks. pages 561- 565, Sept. 2005.
[2]	T. Hayakawa. Vegeta-tion control through selective elimination of large-size weeds on embankments using growth retardant. Quarterly Report of RTRI (Railway Technical Research Institute), Vol. 48:240–243, 2007.
[3]	Swedish Rail Administration. Manual. Banverket. BVH 827.1 - Handbok om vegetation. 2000. Administrator: Berggren Anne-Cathrine.
[4]	Swedish Rail Administration. Manual. Banverket. BVH 827.2 - Behovsanalys infor vegetationsreglering. 2001.
[5]	Swedish Rail Administration. Regulation. Banverket. BVF 807.2 - Sakerhetsbesiktning av fasta anlaggningar. 2005.
[6]	Lundh, Jan-Erik. [Lic. of Science in Forestry and Vegetation Engineer at Trafikverket, Sweden.] Interview. 28 April 2011.
[7]	Rafael C. Gonzalez and Richard E. Woods. Digital Image Processing (3rd Edition). Prentice Hall, August 2007.
[8]	E. S. Andersen. Systems Development - Principles, Methods, and Techniques. Lund: Studentlitteratur., 1994.
[9]	B. W. Boehm. A spiral model of software development and enhancement. Computer, 21(5):61 –72, May 1988.
[10]	Hasan Fleyeh. Traffic and Road Sign Recognition. PhD thesis, Napier University, Scotland, UK, July 2008.
[11]	Nobuyuki Otsu. A threshold selection method from gray-level histograms. Systems, Man and Cybernetics, IEEE Transactions on, 9(1):62 –66, jan. 1979.
[12]	John Canny. A computational approach to edge detection. Pattern Analysis and Machine Intelligence, IEEE Transactions on, PAMI-8(6):679 - 698, nov. 1986.
[13]	Richard O. Duda and Peter E. Hart. Use of the hough transformation to detect lines and curves in pictures. Commun. ACM, 15(1):11–15, 1972.
[14]	C.L. Elzinga, D.W. Salzer, and J.W. Willoughbyh. Measuring and monitoring plant populations. Technical Reference 1730-1 BLM/RS/ST-98/005+1730 (5.1 MB), Bureau of Land Man-agement. Denver, Colorado. USDI, BLM, 1998.
[15]	C.D. Bonham. Measurements for terrestrial vegetation. Wiley Inters-cience publication. Wiley, 989. ISBN 9780471048800.