Autonomous Rail Track Inspection using Vision Based System
- 1 October 2006
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
This paper proposes a rail track inspection technique using automated video analysis. This system is aimed to replace manual visual checks performed by the railway engineers for track inspection. We suggest a combination of image processing and analysis methods to achieve high performance automated rail track inspection. This paper addresses the problem of finding missing clips and finding blue clips which have been recently replaced in place of damaged clips. The experimental results show high performance in machine vision based inspection on a large sample of real train videoKeywords
This publication has 5 references indexed in Scilit:
- Eye-Movement Analysis of Track Monitoring Patterns of Night Train Operators: Effects of Geographic Knowledge and FatigueProceedings of the Human Factors and Ergonomics Society Annual Meeting, 2000
- Composite real-time image processing for railways track profile measurementIEEE Transactions on Instrumentation and Measurement, 2000
- Electronic BAR Gauge: a customized optical rail profile measurement system for rail-grinding applicationsPublished by SPIE-Intl Soc Optical Eng ,1995
- Noncontact technology for track speed rail measurements: ORIANPublished by SPIE-Intl Soc Optical Eng ,1995
- A Computational Approach to Edge DetectionIeee Transactions On Pattern Analysis and Machine Intelligence, 1986