Machine Vision Inspection of Railroad Track

Railroad engineering practices and Federal Railroad Administration (FRA) regulations require track to be inspected for physical defects at specified intervals, which may be as often as twice per week. Most of these inspections are conducted visually by railroad track inspectors and include detecting defects relating to the ballast section, ties, fasteners, rail, and special trackwork. Enhancements to the current manual inspection process are possible using machine-vision technology, which consists of recording digital images of track elements of interest and analyzing them using custom algorithms to identify defects or their symptoms. Based on analysis of FRA accident data, discussion with railroad track engineering experts and consultation with Association of American Railroads researchers, this project focuses on using machine vision to detect irregularities and defects in wood-tie fasteners, rail anchors, crib ballast, and turnout components. Development of a machine-vision-based inspection system will permit more efficient, effective, and objective inspection of these track elements. The system will be adaptable to inspect in accordance with FRA track safety regulations as well as railroad-specific track standards that may involve additional parameters of interest. Also, because data will be stored digitally, recall and quantitative comparative analysis is possible thereby enabling relative comparisons and trend analysis. This will enhance the ability for longer-term predictive assessment of the health of the track system and its components, and lead to more informed preventative maintenance strategies and a greater understanding of track structure degradation and failure modes.


  • English

Media Info

  • Media Type: Web
  • Edition: Final Report
  • Features: Figures; Photos; References;
  • Pagination: 46p

Subject/Index Terms

Filing Info

  • Accession Number: 01342820
  • Record Type: Publication
  • Report/Paper Numbers: NEXTRANS Project No. 0281Y02
  • Contract Numbers: DTRT07-G-005 (Grant)
  • Files: UTC, NTL, TRIS, USDOT
  • Created Date: Jun 14 2011 2:58PM