Delaunay Triangles Model for image-based motion retargeting

Dong Roon Lee, Soon Ki Jung

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

Abstract

We present an automatie system far retargeting a human body extracted from an image sequence into a new character in a still image. In contrast to analysing the articulated motion of its skeleton in the previous vision-based human body tracking and posture recognition system, we use direct 2-D image warping based on a silhouette. At first, we represent the performer's silhouette with the Delaunay Triangles Model (DTM) of which the boundary points are the critical points of the silhouette. We then use a set of affine transformations of Delaunay triangles far the human body motion, which is applied to a new character for the deformation of the subject's DTM. The final animation of the subject is texture mapped using backward Radial Basis Functions (RBFs). Although our algorithm presented in this paper is not applicable to the human body with self-occluded motion, it allows believable photo-realistic motion retargeting.

Original languageEnglish
Title of host publicationDeformable Avatars - IFlP TC5/WG5.10 DEFORM 2000 Workshop and AVATARS 2000 Workshop
PublisherSpringer New York LLC
Pages158-168
Number of pages11
ISBN (Print)9781475749304
DOIs
StatePublished - 2001
EventIFlP TC5/WG5.10 Workshop on Deformable Avatars, DEFORM 2000 -Followed by AVATARS 2000 - Geneva, Switzerland
Duration: 30 Nov 20001 Dec 2000

Publication series

NameIFIP Advances in Information and Communication Technology
Volume68
ISSN (Print)1868-4238

Conference

ConferenceIFlP TC5/WG5.10 Workshop on Deformable Avatars, DEFORM 2000 -Followed by AVATARS 2000
Country/TerritorySwitzerland
CityGeneva
Period30/11/001/12/00

Keywords

  • Character animation and image-based modelling and rendering
  • Delaunay triangulation
  • Motion estimation
  • Vision based motion captlire

Fingerprint

Dive into the research topics of 'Delaunay Triangles Model for image-based motion retargeting'. Together they form a unique fingerprint.

Cite this