Automated visual inspection of railroad tracks

Esther Resendiz, John M. Hart, Narendra Ahuja

Research output: Contribution to journalArticle

Abstract

Thousands of miles of railroad track must be inspected twice weekly by a human inspector to maintain safety standards. A computer vision system, consisting of field-acquired video and subsequent analysis, could improve the efficiency of the current methods. Such a system is prototyped, and the following challenges are addressed: the detection, segmentation, and defect assessment of track components whose appearance vary across different tracks and the identification and inspection of special track areas such as track turnouts. An algorithm that utilizes the periodic manner in which track components repeat in an inspection video is developed. Spectral estimation and signal-processing methods are used to provide robust detection of the periodically occurring track components. Results are demonstrated on field-acquired images and video.

Original languageEnglish (US)
Article number6419832
Pages (from-to)751-760
Number of pages10
JournalIEEE Transactions on Intelligent Transportation Systems
Volume14
Issue number2
DOIs
StatePublished - Jan 30 2013

Fingerprint

Railroad tracks
Inspection
Computer vision
Signal processing
Defects

Keywords

  • Railroad track inspection
  • spectral estimation

ASJC Scopus subject areas

  • Automotive Engineering
  • Mechanical Engineering
  • Computer Science Applications

Cite this

Automated visual inspection of railroad tracks. / Resendiz, Esther; Hart, John M.; Ahuja, Narendra.

In: IEEE Transactions on Intelligent Transportation Systems, Vol. 14, No. 2, 6419832, 30.01.2013, p. 751-760.

Research output: Contribution to journalArticle

@article{e1941624fbaa4879a6ac060d88a4d051,
title = "Automated visual inspection of railroad tracks",
abstract = "Thousands of miles of railroad track must be inspected twice weekly by a human inspector to maintain safety standards. A computer vision system, consisting of field-acquired video and subsequent analysis, could improve the efficiency of the current methods. Such a system is prototyped, and the following challenges are addressed: the detection, segmentation, and defect assessment of track components whose appearance vary across different tracks and the identification and inspection of special track areas such as track turnouts. An algorithm that utilizes the periodic manner in which track components repeat in an inspection video is developed. Spectral estimation and signal-processing methods are used to provide robust detection of the periodically occurring track components. Results are demonstrated on field-acquired images and video.",
keywords = "Railroad track inspection, spectral estimation",
author = "Esther Resendiz and Hart, {John M.} and Narendra Ahuja",
year = "2013",
month = "1",
day = "30",
doi = "10.1109/TITS.2012.2236555",
language = "English (US)",
volume = "14",
pages = "751--760",
journal = "IEEE Transactions on Intelligent Transportation Systems",
issn = "1524-9050",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Automated visual inspection of railroad tracks

AU - Resendiz, Esther

AU - Hart, John M.

AU - Ahuja, Narendra

PY - 2013/1/30

Y1 - 2013/1/30

N2 - Thousands of miles of railroad track must be inspected twice weekly by a human inspector to maintain safety standards. A computer vision system, consisting of field-acquired video and subsequent analysis, could improve the efficiency of the current methods. Such a system is prototyped, and the following challenges are addressed: the detection, segmentation, and defect assessment of track components whose appearance vary across different tracks and the identification and inspection of special track areas such as track turnouts. An algorithm that utilizes the periodic manner in which track components repeat in an inspection video is developed. Spectral estimation and signal-processing methods are used to provide robust detection of the periodically occurring track components. Results are demonstrated on field-acquired images and video.

AB - Thousands of miles of railroad track must be inspected twice weekly by a human inspector to maintain safety standards. A computer vision system, consisting of field-acquired video and subsequent analysis, could improve the efficiency of the current methods. Such a system is prototyped, and the following challenges are addressed: the detection, segmentation, and defect assessment of track components whose appearance vary across different tracks and the identification and inspection of special track areas such as track turnouts. An algorithm that utilizes the periodic manner in which track components repeat in an inspection video is developed. Spectral estimation and signal-processing methods are used to provide robust detection of the periodically occurring track components. Results are demonstrated on field-acquired images and video.

KW - Railroad track inspection

KW - spectral estimation

UR - http://www.scopus.com/inward/record.url?scp=84878697215&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878697215&partnerID=8YFLogxK

U2 - 10.1109/TITS.2012.2236555

DO - 10.1109/TITS.2012.2236555

M3 - Article

AN - SCOPUS:84878697215

VL - 14

SP - 751

EP - 760

JO - IEEE Transactions on Intelligent Transportation Systems

JF - IEEE Transactions on Intelligent Transportation Systems

SN - 1524-9050

IS - 2

M1 - 6419832

ER -