Demonstration of Commercial-Off-The-Shelf Change Detection on Railway Images

This study, conducted jointly by ENSCO, Inc. and Harris Corporation, assessed the potential benefits of applying commercially available change detection software to railway machine vision images. Change detection involves registering “Before” and “After” images on a pixel-by-pixel basis to isolate changed areas. Two modes of change detection were assessed: intensity-based detection that identifies change where pixel intensity differs and thematic-based detection that identifies change where predetermined pixel themes (e.g., concrete, ballast, etc.) occur. The intensity-based mode has shown potential for use on rail-based images; the thematic-based mode has shown potential to help fill a supporting role of filtering non-relevant changes.

  • Record URL:
  • Record URL:
  • Corporate Authors:

    ENSCO, Incorporated

    5400 Port Royal Road
    Springfield, VA  United States  22151

    Harris Corporation

    385 Interlocken Crescent, Suite 300
    Broomfield, CO  United States  80021

    Federal Railroad Administration

    Office of Railroad Policy and Development, 1200 New Jersey Avenue, SE
    Washington, DC  United States  20590

    Federal Railroad Administration

    Office of Research, Development, and Technology
    Washington, DC  United States 
  • Authors:
    • Henderson, Herbert
    • Borsholm, Atle
  • Publication Date: 2019-7

Language

  • English

Media Info

  • Media Type: Digital/other
  • Edition: Final Report; Technical Report
  • Features: Appendices; Figures; Photos; Tables;
  • Pagination: 123p

Subject/Index Terms

Filing Info

  • Accession Number: 01710459
  • Record Type: Publication
  • Report/Paper Numbers: DOT/FRA/ORD-19/22, SERV-REPT-0001686
  • Contract Numbers: DTFR53-17-C-00001
  • Files: NTL, TRIS, ATRI, USDOT
  • Created Date: Jul 2 2019 12:15PM