Semi-supervised rail defect detection from imbalanced image data

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientific

17 Citations (Scopus)
110 Downloads (Pure)

Abstract

Rail defect detection by video cameras has recently gained much attention in both
academia and industry. Rail image data has two properties. It is highly imbalanced towards the non-defective class and it has a large number of unlabeled data samples available for semisupervised learning techniques. In this paper we investigate if positive defective candidates selected from the unlabeled data can help improve the balance between the two classes and gain performance on detecting a specic type of defects called Squats. We compare data sampling techniques as well and conclude that the semi-supervised techniques are a reasonable alternative for improving performance on applications such as rail track Squat detection from image data.
Original languageEnglish
Title of host publicationProceedings of the 14th IFAC Symposium on Control in Transportation Systems, CTS 2016, Istanbul, Turkey
EditorsTankut Acarman
Pages1-6
Number of pages6
Publication statusPublished - 2016
Event14th IFAC Symposium on Control in Transportation Systems - ITU Faculty of Architecture, Istanbul, Turkey
Duration: 18 May 201620 May 2016
http://www.cts2016.org/en/

Conference

Conference14th IFAC Symposium on Control in Transportation Systems
Abbreviated titleCTS 2016
CountryTurkey
CityIstanbul
Period18/05/1620/05/16
Internet address

Keywords

  • imbalance data
  • semi-supervised learning
  • rail image data
  • rail defect detection

Fingerprint Dive into the research topics of 'Semi-supervised rail defect detection from imbalanced image data'. Together they form a unique fingerprint.

Cite this