Markerless 3D hand posture estimation from monocular video by two-level searching

Iek Kuong Pun, I-Chen Lin, Tsung Hsien Tang

Research output: Contribution to conferencePaperpeer-review

Abstract

In this paper, a marker less 3D hand tracking system for monocular RGB video is presented. We propose a novel two-level approach to efficiently grasp the personal characteristics and high varieties of hand postures. Our system first searches the approximate nearest neighbors in a small personalized real-hand image set, and retrieves more details from a large synthetic 3D hand posture database. Temporal consistency property is also utilized for disambiguating and noise reduction. Our prototype system can approximate hand poses including rigid and non-rigid out-of-image-plane rotation, slow and fast gesture changing during rotation. It can also recover from a short-Term missing hand situation in an interactive rate.

Original languageEnglish
Pages204-211
Number of pages8
DOIs
StatePublished - 1 Jan 2013
Event13th International Conference on Computer-Aided Design and Computer Graphics, CAD/Graphics 2013 - Hong Kong, China
Duration: 16 Nov 201318 Nov 2013

Conference

Conference13th International Conference on Computer-Aided Design and Computer Graphics, CAD/Graphics 2013
CountryChina
CityHong Kong
Period16/11/1318/11/13

Keywords

  • 3D gesture
  • advanced interface
  • hand tracking

Fingerprint Dive into the research topics of 'Markerless 3D hand posture estimation from monocular video by two-level searching'. Together they form a unique fingerprint.

Cite this