Joint 3D-reconstruction and background separation in multiple views using graph cuts

dc.contributor.authorGoldlücke, Bastian
dc.contributor.authorMagnor, Marcus A.
dc.date.accessioned2017-12-21T08:17:17Z
dc.date.available2017-12-21T08:17:17Z
dc.date.issued2003eng
dc.description.abstractThis paper deals with simultaneous depth map estimation and background separation in a multi-view setting with several fixed calibrated cameras, two problems which have previously been addressed separately. We demonstrate that their strong interdependency can be exploited elegantly by minimizing a discrete energy functional, which evaluates both properties at the same time. Our algorithm is derived from the powerful "multi-camera scene reconstruction via graph cuts" algorithm presented by Kolmogorov and Zabih (2002). Experiments with both real-world as well as synthetic scenes demonstrate that the presented combined approach yields even more correct depth estimates. In particular, the additional information gained by taking background into account increases considerably the algorithm's robustness against noise.eng
dc.description.versionpublishedeng
dc.identifier.doi10.1109/CVPR.2003.1211419eng
dc.identifier.urihttps://kops.uni-konstanz.de/handle/123456789/40992
dc.language.isoengeng
dc.subjectLayout, Image reconstruction, Cameras, Stereo vision, Pixel, Computer vision, Iterative algorithms, Yield estimation, Noise robustness, Background noiseeng
dc.subject.ddc004eng
dc.titleJoint 3D-reconstruction and background separation in multiple views using graph cutseng
dc.typeINPROCEEDINGSeng
dspace.entity.typePublication
kops.citation.bibtex
@inproceedings{Goldlucke2003Joint-40992,
  year={2003},
  doi={10.1109/CVPR.2003.1211419},
  title={Joint 3D-reconstruction and background separation in multiple views using graph cuts},
  isbn={0-7695-1900-8},
  issn={1063-6919},
  publisher={IEEE Computer Society},
  address={Los Alamitos, California},
  booktitle={Proceedings : 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 18 - 20 June 2003, Madison, Wisconsin ; Vol. 1},
  pages={I-683--I-688},
  author={Goldlücke, Bastian and Magnor, Marcus A.}
}
kops.citation.iso690GOLDLÜCKE, Bastian, Marcus A. MAGNOR, 2003. Joint 3D-reconstruction and background separation in multiple views using graph cuts. CVPR 2003. Madison, Wis., 18. Juni 2003 - 20. Juni 2003. In: Proceedings : 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 18 - 20 June 2003, Madison, Wisconsin ; Vol. 1. Los Alamitos, California: IEEE Computer Society, 2003, pp. I-683-I-688. ISSN 1063-6919. ISBN 0-7695-1900-8. Available under: doi: 10.1109/CVPR.2003.1211419deu
kops.citation.iso690GOLDLÜCKE, Bastian, Marcus A. MAGNOR, 2003. Joint 3D-reconstruction and background separation in multiple views using graph cuts. CVPR 2003. Madison, Wis., Jun 18, 2003 - Jun 20, 2003. In: Proceedings : 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 18 - 20 June 2003, Madison, Wisconsin ; Vol. 1. Los Alamitos, California: IEEE Computer Society, 2003, pp. I-683-I-688. ISSN 1063-6919. ISBN 0-7695-1900-8. Available under: doi: 10.1109/CVPR.2003.1211419eng
kops.citation.rdf
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/40992">
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/40992"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Magnor, Marcus A.</dc:creator>
    <dcterms:title>Joint 3D-reconstruction and background separation in multiple views using graph cuts</dcterms:title>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:language>eng</dc:language>
    <dc:creator>Goldlücke, Bastian</dc:creator>
    <dcterms:issued>2003</dcterms:issued>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2017-12-21T08:17:17Z</dc:date>
    <dcterms:abstract xml:lang="eng">This paper deals with simultaneous depth map estimation and background separation in a multi-view setting with several fixed calibrated cameras, two problems which have previously been addressed separately. We demonstrate that their strong interdependency can be exploited elegantly by minimizing a discrete energy functional, which evaluates both properties at the same time. Our algorithm is derived from the powerful "multi-camera scene reconstruction via graph cuts" algorithm presented by Kolmogorov and Zabih (2002). Experiments with both real-world as well as synthetic scenes demonstrate that the presented combined approach yields even more correct depth estimates. In particular, the additional information gained by taking background into account increases considerably the algorithm's robustness against noise.</dcterms:abstract>
    <dc:contributor>Goldlücke, Bastian</dc:contributor>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2017-12-21T08:17:17Z</dcterms:available>
    <dc:contributor>Magnor, Marcus A.</dc:contributor>
  </rdf:Description>
</rdf:RDF>
kops.conferencefieldCVPR 2003, 18. Juni 2003 - 20. Juni 2003, Madison, Wis.deu
kops.date.conferenceEnd2003-06-20eng
kops.date.conferenceStart2003-06-18eng
kops.flag.knbibliographyfalse
kops.location.conferenceMadison, Wis.eng
kops.sourcefield<i>Proceedings : 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 18 - 20 June 2003, Madison, Wisconsin ; Vol. 1</i>. Los Alamitos, California: IEEE Computer Society, 2003, pp. I-683-I-688. ISSN 1063-6919. ISBN 0-7695-1900-8. Available under: doi: 10.1109/CVPR.2003.1211419deu
kops.sourcefield.plainProceedings : 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 18 - 20 June 2003, Madison, Wisconsin ; Vol. 1. Los Alamitos, California: IEEE Computer Society, 2003, pp. I-683-I-688. ISSN 1063-6919. ISBN 0-7695-1900-8. Available under: doi: 10.1109/CVPR.2003.1211419deu
kops.sourcefield.plainProceedings : 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 18 - 20 June 2003, Madison, Wisconsin ; Vol. 1. Los Alamitos, California: IEEE Computer Society, 2003, pp. I-683-I-688. ISSN 1063-6919. ISBN 0-7695-1900-8. Available under: doi: 10.1109/CVPR.2003.1211419eng
kops.title.conferenceCVPR 2003eng
relation.isAuthorOfPublicationc4ecb499-9c85-4481-832e-af061f18cbdc
relation.isAuthorOfPublication.latestForDiscoveryc4ecb499-9c85-4481-832e-af061f18cbdc
source.bibliographicInfo.fromPageI-683eng
source.bibliographicInfo.toPageI-688eng
source.identifier.isbn0-7695-1900-8eng
source.identifier.issn1063-6919eng
source.publisherIEEE Computer Societyeng
source.publisher.locationLos Alamitos, Californiaeng
source.titleProceedings : 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 18 - 20 June 2003, Madison, Wisconsin ; Vol. 1eng

Dateien