Profile parameters of wheelset detection for high speed freight train

Kai Yang; Li Ma; Xiaorong Gao; Li Wang

doi:10.1117/12.952474

8 June 2012 Profile parameters of wheelset detection for high speed freight train

Kai Yang, Li Ma, Xiaorong Gao, Li Wang

Proceedings Volume 8334, Fourth International Conference on Digital Image Processing (ICDIP 2012); 83341W (2012) https://doi.org/10.1117/12.952474
Event: Fourth International Conference on Digital Image Processing (ICDIP 2012), 2012, Kuala Lumpur, Malaysia

Abstract

Because of freight train, in China, transports goods on railway freight line throughout the country, it does not depart from or return to engine shed during a long phase, thus we cannot monitor the quality of wheel set effectively. This paper provides a system which uses leaser and high speed camera, applies no-contact light section technology to get precise wheel set profile parameters. The paper employs clamping-track method to avoid complex railway ballast modification project. And detailed descript an improved image-tracking algorithm to extract central line from profile curve. For getting one pixel width and continuous line of the profile curve, uses local gray maximum points as direction control points to direct tracking direction. The results based on practical experiment show the system adapted to detection environment of high speed and high vibration, and it can effectively detect the wheelset geometric parameters with high accuracy. The system fills the gaps in wheel set detection for freight train in main line and has an enlightening function on monitoring the quality of wheel set.

Citation Download Citation

Kai Yang, Li Ma, Xiaorong Gao, and Li Wang "Profile parameters of wheelset detection for high speed freight train", Proc. SPIE 8334, Fourth International Conference on Digital Image Processing (ICDIP 2012), 83341W (8 June 2012); https://doi.org/10.1117/12.952474

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available