Two Approaches for Characterizing Images of Rail Surface Flaws

by Roemer Alfelor, Camegie Mellon Univ, Pittsburgh, United States,
Thomas Short, Camegie Mellon Univ, Pittsburgh, United States,
Behnam Motazed, Camegie Mellon Univ, Pittsburgh, United States,
Sue McNeil, Camegie Mellon Univ, Pittsburgh, United States,



Document Type: Proceeding Paper

Part of: Applications of Advanced Technologies in Transportation Engineering

Abstract:

Rail surface flaws can be removed by grinding to improve the life of rail and provide a safe, smooth running surface. To avoid time consuming and costly visual inspection in the determination of grinding strategies, high speed automated data collection has been explored. This paper describes and compares a frame-by-frame approach to the analysis of rail surface images obtained in the field using a high speed video camera with a pixel-by-pixel method.

Subject Headings: Rail transportation | Railroad tracks | Computer vision and image processing | Inspection | Data collection | Construction management | Automation and robotics

Services: Buy this book/Buy this article

 

Return to search