Space-Time Multi-Resolution Banded Graph-Cut for Fast Segmentation. (Conference Poster)

Show simple item record

dc.contributor.author Vaudrey, Tobi en
dc.contributor.author Gruber, Daniel en
dc.contributor.author Wedel, Andreas en
dc.contributor.author Klappstein, Jens en
dc.date.accessioned 2008-12-16T21:41:25Z en
dc.date.available 2008-12-16T21:41:25Z en
dc.date.issued 2008 en
dc.identifier.citation DAGM 2008 Pattern Recognition: 30th DAGM Symposium, Munich, Germany, June 2008. Poster Session 2 Thursday 12 June 2008. en
dc.identifier.uri http://hdl.handle.net/2292/3275 en
dc.description Conference Details: 30th Annual Symposium of the German Association for Pattern Recognition DAGM Munich, Germany, June 2008. http://www.dagm2008.org/ en
dc.description.abstract Applying real-time segmentation is a major issue when processing every frame of image sequences. In this paper, we propose a modi cation of the well known graph-cut algorithm to improve speed for discrete segmentation. Our algorithm yields real-time segmentation, using graph-cut, by performing a single cut on an image with regions of di erent resolutions, combining space-time pyramids and narrow bands. This is especially suitable for image sequences, as segment borders in one image are re ned in the next image. The fast computation time allows one to use information contained in every image frame of an input image stream at 20 Hz, on a standard PC. The algorithm is applied to traf- c scenes, using a monocular camera installed in a moving vehicle. Our results show the segmentation of moving objects with similar results to standard graph-cut, but with improved speed. en
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. en
dc.rights.uri https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm en
dc.title Space-Time Multi-Resolution Banded Graph-Cut for Fast Segmentation. (Conference Poster) en
dc.type Conference Poster en
dc.subject.marsden Fields of Research::280000 Information, Computing and Communication Sciences en
dc.description.version AM - Authors Manuscript en
dc.rights.holder Copyright: Tobi Vaudrey en
dc.rights.accessrights http://purl.org/eprint/accessRights/OpenAccess en


Files in this item

Find Full text

This item appears in the following Collection(s)

Show simple item record

Share

Search ResearchSpace


Browse

Statistics