Cited time in webofscience Cited time in scopus

Full metadata record

DC Field Value Language Lee, CH[Lee, Chung-Hee] ko Lim, YC[Lim, Young-Chul] ko Kim, D[Kim, Dongyoung] ko Sohng, KI[Sohng, Kyu-Ik] ko 2017-07-11T06:29:03Z - 2017-04-10 - 2014 -
dc.identifier.citation Elektronika Ir Elektrotechnika, v.20, no.9, pp.54 - 58 -
dc.identifier.issn 1392-1215 -
dc.identifier.uri -
dc.description.abstract Despite significant progress in vehicle detection over the last few decades, vehicle detection performance in heavy traffic is still inadequate. In this paper, we propose a new algorithm for vehicle detection in heavy traffic to improve detection performance. It uses two proposed segmentation methods, namely, the disparity map-based bird's-eye-view mapping segmentation method and the edge distance weighted conditional random field (CRF)-based segmentation method. Our experimental results show that the proposed algorithm outperforms conventional algorithms. The improvements in performance range from 10.8 % to 20.5 % increase in F-measure. -
dc.publisher Kaunas University of Technology -
dc.subject Image Segmentation -
dc.subject Intelligent Vehicle -
dc.subject Object Recognition -
dc.subject Stereo Image Processing -
dc.title Improved Vehicle Detection Algorithm in Heavy Traffic for Intelligent Vehicle -
dc.type Article -
dc.identifier.doi 10.5755/j01.eee.20.9.3734 -
dc.identifier.wosid 000345356800011 -
dc.identifier.scopusid 2-s2.0-84911437121 -
dc.type.local Article(Overseas) -
dc.type.rims ART -
dc.description.journalClass 1 -
dc.contributor.nonIdAuthor Sohng, KI[Sohng, Kyu-Ik] -
dc.identifier.citationVolume 20 -
dc.identifier.citationNumber 9 -
dc.identifier.citationStartPage 54 -
dc.identifier.citationEndPage 58 -
dc.identifier.citationTitle Elektronika Ir Elektrotechnika -
dc.type.journalArticle Article -
dc.contributor.affiliatedAuthor Lee, CH[Lee, Chung-Hee] -
dc.contributor.affiliatedAuthor Lim, YC[Lim, Young-Chul] -
dc.contributor.affiliatedAuthor Kim, D[Kim, Dongyoung] -


  • twitter
  • facebook
  • mendeley

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.