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

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

doi:10.1109/CADGraphics.2013.34

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

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

Department of Computer Science

Research output: Contribution to conference › Paper › peer-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 language	English
Pages	204-211
Number of pages	8
DOIs	https://doi.org/10.1109/CADGraphics.2013.34
State	Published - 2013
Event	13th International Conference on Computer-Aided Design and Computer Graphics, CAD/Graphics 2013 - Hong Kong, China Duration: 16 Nov 2013 → 18 Nov 2013

Conference

Conference	13th International Conference on Computer-Aided Design and Computer Graphics, CAD/Graphics 2013
Country/Territory	China
City	Hong Kong
Period	16/11/13 → 18/11/13

Keywords

3D gesture
advanced interface
hand tracking

Access to Document

10.1109/CADGraphics.2013.34

Cite this

@conference{9725bad3239d4a27840abd8a6fe96a68,

title = "Markerless 3D hand posture estimation from monocular video by two-level searching",

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.",

keywords = "3D gesture, advanced interface, hand tracking",

author = "Pun, {Iek Kuong} and I-Chen Lin and Tang, {Tsung Hsien}",

year = "2013",

doi = "10.1109/CADGraphics.2013.34",

language = "English",

pages = "204--211",

note = "13th International Conference on Computer-Aided Design and Computer Graphics, CAD/Graphics 2013 ; Conference date: 16-11-2013 Through 18-11-2013",

}

TY - CONF

T1 - Markerless 3D hand posture estimation from monocular video by two-level searching

AU - Pun, Iek Kuong

AU - Lin, I-Chen

AU - Tang, Tsung Hsien

PY - 2013

Y1 - 2013

N2 - 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.

AB - 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.

KW - 3D gesture

KW - advanced interface

KW - hand tracking

UR - http://www.scopus.com/inward/record.url?scp=84901443400&partnerID=8YFLogxK

U2 - 10.1109/CADGraphics.2013.34

DO - 10.1109/CADGraphics.2013.34

M3 - Paper

AN - SCOPUS:84901443400

SP - 204

EP - 211

T2 - 13th International Conference on Computer-Aided Design and Computer Graphics, CAD/Graphics 2013

Y2 - 16 November 2013 through 18 November 2013

ER -

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

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this