Segmentation through edge-linking: Segmentation for video-based driver assistance systems

Andreas Laika, Adrian Taruttis, Walter Stechele

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This work aims to develop an image segmentation method to be used in automotive driver assistance svstems. In this context it is possible to incorporate a priori knovvledge from other sensors to ease the problem of local-izing objects and to improve the results. It is however desired to product accurate segmentations displaving good edge localization and to have real time capabilities. An edge-segment grouping method is presented to meetthese aims. Edges of varying strength aredetected initiallv. In various preprocessing steps edge-segments are formed. A sparse graph is generated from those using perceptual grouping phenomena. Closed contours are formed by solving the shortest path problem. Using test data fitting to the application domain, it is shown that the proposed method provides more accurate results than the vvell-knovn Gradient Vector Field Snakes.

Original languageEnglish
Title of host publicationIMAGAPP 2009 - Proceedings of the 1st International Conference on Computer Imaging Theory and Applications
Pages43-49
Number of pages7
StatePublished - 2009
Event1st International Conference on Computer Imaging Theory and Applications, IMAGAPP 2009 - Lisboa, Portugal
Duration: 5 Feb 20098 Feb 2009

Publication series

NameIMAGAPP 2009 - Proceedings of the 1st International Conference on Computer Imaging Theory and Applications

Conference

Conference1st International Conference on Computer Imaging Theory and Applications, IMAGAPP 2009
Country/TerritoryPortugal
CityLisboa
Period5/02/098/02/09

Keywords

  • Driver assistance
  • Edge linking
  • Object recognition
  • Segmentation

Fingerprint

Dive into the research topics of 'Segmentation through edge-linking: Segmentation for video-based driver assistance systems'. Together they form a unique fingerprint.

Cite this