du.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A contour-based separation of vertically attached traffic signs
Dalarna University, School of Technology and Business Studies, Computer Engineering.ORCID iD: 0000-0002-1429-2345
2008 (English)In: 34th Annual Conference of the IEEE Industrial Electronics Society, vols 1-5, proceedings, 2008, Vol. 1-5, p. 1747-1752Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents a contour-based approach to separate vertically attached traffic signs. The algorithm is based on using binary images which are generated by any color segmentation algorithm to represent objects which could be candidate traffic signs. Since all traffic signs are similar about their vertical axis, an improved cross-correlation algorithm is invoked to determine this similarity and filters traffic sign candidates. Shape decomposition is used to smooth the contour of the candidate object iteratively in order to reduce white noise. Flipping point detection algorithm which locates black noise along the smoothed contour and the curve prediction algorithm are invoked to determine the final cut points. A separation accuracy of 94% is achieved by the algorithm. In this experiment more that 70000 images of different traffic sign combinations are invoked to achieve this result. The algorithm is tested on one-sign images, two-sign images, and three-sign images which are combined together for the purpose of testing this algorithm.

Place, publisher, year, edition, pages
2008. Vol. 1-5, p. 1747-1752
Keyword [en]
traffic sign recognition, cross correlation, contour based algorithm
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:du-3698ISI: 000266229301067OAI: oai:dalea.du.se:3698DiVA, id: diva2:521913
Conference
34th Annual Conference of the IEEE Industrial Electronics Society (IECON 2008), Orlando, USA, Nov. 10-13, 2008
Available from: 2009-02-05 Created: 2009-02-05 Last updated: 2018-01-12Bibliographically approved

Open Access in DiVA

No full text in DiVA

Authority records BETA

Fleyeh, Hasan

Search in DiVA

By author/editor
Fleyeh, Hasan
By organisation
Computer Engineering
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 556 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf