Computational & Technology Resources
an online resource for computational,
engineering & technology publications
Civil-Comp Proceedings
ISSN 1759-3433
CCP: 104
PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE
Edited by: J. Pombo
Paper 92

Research on the Vehicular Detection Technology of Rail Wear based on Machine Vision

H. Wang, W.D. Wang and Y.F. Zhao

Infrastructure Inspection Centre, Chinese Academy of Railway Science, Beijing, China

Full Bibliographic Reference for this paper
H. Wang, W.D. Wang, Y.F. Zhao, "Research on the Vehicular Detection Technology of Rail Wear based on Machine Vision", in J. Pombo, (Editor), "Proceedings of the Second International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Stirlingshire, UK, Paper 92, 2014. doi:10.4203/ccp.104.92
Keywords: machine vision, vehicular detection system, rail wear, non-contact measurement, image processing, coordinate transformation.

Summary
This paper proposes a new type of vehicular non-contact rail wear detection system based on machine vision (close range photogrammetry and image processing) techniques. First, this paper introduces the detection principle of the technology including: the overall structure of the technology design, measurement model and the introduction of structural light measurement. The technology consists of three modules: an image acquisition module, an image processing and data analysis module, and a results display module. The second part provides a detailed explanation of image processing, including image smoothing, image segmentation, image thinning and so on. The third part of the paper introduces and analyzes the application situation and detection results of wear measurements. The technology has been installed in ten monitoring vehicles at present. The Beijing Shanghai, Wuhan Guangzhou high-speed railway, Datong Qinhuangdao heavy haul railway and many existing railways have been regularly using this technology. The repeatability precision of it is less than 0.2mm.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description