Wrinkle based skeleton embedding method for refined human hand

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

Abstract

It has been always a challenge to extract or generate a skeleton from a mesh. Most skeleton extraction methods are aimed at articulated character models, which are not well suitable for refined hand model. We proposed a novel automatic method for skeleton extraction of refined human hand meshes. Given a refined human hand meshes, we first use an automatic rigging system to extract a coarse skeleton graph. Then we run a refinement algorithm to the graph by tracking the wrinkles near the joints, so that the coarse skeleton graph is adjusted and refined. Finally, a match algorithm is applied to produce joint frames of the skeleton graph. Finally, joint frames are attached to support rotation. Our method produces reasonable skeleton on refined human hands while delivering an acceptable performance, enabling further use of hand pose animation by any skeleton-based methods.

Original languageEnglish
Title of host publicationProceedings - 2016 International Conference on Virtual Reality and Visualization, ICVRV 2016
EditorsDandan Ding, Dangxiao Wang, Jian Chen, Xun Luo
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages183-189
Number of pages7
ISBN (Electronic)9781509051885
DOIs
StatePublished - 1 Jun 2017
Event6th International Conference on Virtual Reality and Visualization, ICVRV 2016 - Hangzhou, Zhejiang, China
Duration: 24 Sep 201626 Sep 2016

Publication series

NameProceedings - 2016 International Conference on Virtual Reality and Visualization, ICVRV 2016

Conference

Conference6th International Conference on Virtual Reality and Visualization, ICVRV 2016
Country/TerritoryChina
CityHangzhou, Zhejiang
Period24/09/1626/09/16

Keywords

  • Hand skeleton extraction
  • Skeleton graph refinement
  • Wrinkle detection

Fingerprint

Dive into the research topics of 'Wrinkle based skeleton embedding method for refined human hand'. Together they form a unique fingerprint.

Cite this