6676

Survey on Benchmarks for a GPU Based Multi Camera Stereo Matching Algorithm

Klaus Denker, Georg Umlauf
Computer Graphics Lab, Department of Computer Science, University of Applied Sciences Konstanz, Brauneggerstr. 55, 78462 Konstanz, Germany
Visualization of Large and Unstructured Data Sets – Applications in Geospatial Planning, Modeling and Engineering (IRTG 1131 Workshop), 2011

@InProceedings{denker_et_al:OASIcs:2011:3093,

   author={Klaus Denker and Georg Umlauf},

   title={Survey on Benchmarks for a GPU Based Multi Camera Stereo Matching Algorithm},

   booktitle={Visualization of Large and Unstructured Data Sets – Applications in Geospatial Planning, Modeling and Engineering (IRTG 1131 Workshop)},

   pages={20–26},

   series={OpenAccess Series in Informatics (OASIcs)},

   ISBN={978-3-939897-29-3},

   ISSN={2190-6807},

   year={2011},

   volume={19},

   editor={Ariane Middel and Inga Scheler and Hans Hagen},

   publisher={Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik},

   address={Dagstuhl, Germany},

   URL={http://drops.dagstuhl.de/opus/volltexte/2011/3093},

   doi={http://dx.doi.org/10.4230/OASIcs.VLUDS.2010.20},

   annote={Keywords: Stereo matching, Multi camera, GPU}

}

Download Download (PDF)   View View   Source Source   

863

views

Stereo matching algorithms and multi camera reconstruction algorithms are usually compared using benchmarks. These benchmarks compare the quality of the resulting depth map or reconstructed surface mesh. We describe the differences between several known stereo and multi-view stereo benchmarks and their various datasets. Also the modifications that are necessary to use our own GPU based multi camera stereo matching algorithm with the data from these benchmarks are discussed.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: