Estimating 2D Multi-hand Poses from Single Depth Images

Duan, Le; Shen, Minmin; Cui, Song; Guo, Zhexiao; Deussen, Oliver

Estimating 2D Multi-hand Poses from Single Depth Images

Files

Duan_2-eag9rf9qwzit2.pdf(2.86 MB)

Date

2019

Authors

Duan, Le

Shen, Minmin

Cui, Song

Guo, Zhexiao

Deussen, Oliver

Publication type

Contribution to a conference collection

Publication status

Published

Published in

Computer Vision - ECCV 2018 Workshops : Munich, Germany, September 8-14, 2018, Proceedings, Part VI / Leal-Taixé, Laura; Roth, Stefan (ed.). - Cham : Springer, 2019. - (Lecture Notes in Computer Science ; 11134). - pp. 257-272. - ISSN 0302-9743. - eISSN 1611-3349. - ISBN 978-3-030-11023-9

Abstract

We present a novel framework based on Pictorial Structure (PS) models to estimate 2D multi-hand poses from depth images. Most existing single-hand pose estimation algorithms are either subject to strong assumptions or depend on a weak detector to detect the human hand. We utilize Mask R-CNN to avoid both aforementioned constraints. The proposed framework allows detection of multi-hand instances and localization of hand joints simultaneously. Our experiments show that our method is superior to existing methods.

Subject (DDC)

004 Computer Science

Conference

European Conference on Computer Vision (ECCV) 2018, Sep 8, 2018 - Sep 14, 2018, München

Cite This

ISO 690

DUAN, Le, Minmin SHEN, Song CUI, Zhexiao GUO, Oliver DEUSSEN, 2019. Estimating 2D Multi-hand Poses from Single Depth Images. European Conference on Computer Vision (ECCV) 2018. München, Sep 8, 2018 - Sep 14, 2018. In: LEAL-TAIXÉ, Laura, ed., Stefan ROTH, ed.. Computer Vision - ECCV 2018 Workshops : Munich, Germany, September 8-14, 2018, Proceedings, Part VI. Cham:Springer, pp. 257-272. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-030-11023-9. Available under: doi: 10.1007/978-3-030-11024-6_17

BibTex

@inproceedings{Duan2019Estim-52400,
  year={2019},
  doi={10.1007/978-3-030-11024-6_17},
  title={Estimating 2D Multi-hand Poses from Single Depth Images},
  number={11134},
  isbn={978-3-030-11023-9},
  issn={0302-9743},
  publisher={Springer},
  address={Cham},
  series={Lecture Notes in Computer Science},
  booktitle={Computer Vision - ECCV 2018 Workshops : Munich, Germany, September 8-14, 2018, Proceedings, Part VI},
  pages={257--272},
  editor={Leal-Taixé, Laura and Roth, Stefan},
  author={Duan, Le and Shen, Minmin and Cui, Song and Guo, Zhexiao and Deussen, Oliver}
}

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/123456789/52400">
    <dc:rights>terms-of-use</dc:rights>
    <dc:creator>Cui, Song</dc:creator>
    <dc:creator>Shen, Minmin</dc:creator>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/52400/1/Duan_2-eag9rf9qwzit2.pdf"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-01-14T09:07:38Z</dcterms:available>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/52400/1/Duan_2-eag9rf9qwzit2.pdf"/>
    <dc:contributor>Deussen, Oliver</dc:contributor>
    <dc:creator>Duan, Le</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-01-14T09:07:38Z</dc:date>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dcterms:title>Estimating 2D Multi-hand Poses from Single Depth Images</dcterms:title>
    <dc:creator>Guo, Zhexiao</dc:creator>
    <dcterms:abstract xml:lang="eng">We present a novel framework based on Pictorial Structure (PS) models to estimate 2D multi-hand poses from depth images. Most existing single-hand pose estimation algorithms are either subject to strong assumptions or depend on a weak detector to detect the human hand. We utilize Mask R-CNN to avoid both aforementioned constraints. The proposed framework allows detection of multi-hand instances and localization of hand joints simultaneously. Our experiments show that our method is superior to existing methods.</dcterms:abstract>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:language>eng</dc:language>
    <dc:contributor>Shen, Minmin</dc:contributor>
    <dc:contributor>Cui, Song</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Guo, Zhexiao</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Deussen, Oliver</dc:creator>
    <dcterms:issued>2019</dcterms:issued>
    <dc:contributor>Duan, Le</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/52400"/>
  </rdf:Description>
</rdf:RDF>

Bibliography of Konstanz

Yes