3D hand tracking using Kalman filter in depth space

Sangheon Park, Sunjin Yu, Joongrock Kim, Sungjin Kim, Sang Youn Lee

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

Hand gestures are an important type of natural language used in many research areas such as human-computer interaction and computer vision. Hand gestures recognition requires the prior determination of the hand position through detection and tracking. One of the most efficient strategies for hand tracking is to use 2D visua information such as color and shape. However, visual-sensor-based hand tracking methods are very sensitive when tracking is performed under variable light conditions. Also, as hand movements are made in 3D space, the recognition performance of hand gestures using 2D information is inherently limited. In this article, we propose a novel real-time 3D hand tracking method in depth space using a 3D depth sensor and employing Kalman filter. We detect hand candidates using motion clusters and predefined wave motion, and track hand locations using Kalman filter. To verify the effectiveness of the proposed method, we compare the performance of the proposed method with the visual-based method. Experimental results show that the performance of the proposed method out performs visual-based method.

Original languageEnglish
Article number36
JournalEurasip Journal on Advances in Signal Processing
Volume2012
Issue number1
DOIs
Publication statusPublished - 2012 Dec 1

Fingerprint

Kalman filters
Gesture recognition
Sensors
End effectors
Human computer interaction
Computer vision
Color

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Park, Sangheon ; Yu, Sunjin ; Kim, Joongrock ; Kim, Sungjin ; Lee, Sang Youn. / 3D hand tracking using Kalman filter in depth space. In: Eurasip Journal on Advances in Signal Processing. 2012 ; Vol. 2012, No. 1.
@article{2a87df849ca94b70aa2893799010bf61,
title = "3D hand tracking using Kalman filter in depth space",
abstract = "Hand gestures are an important type of natural language used in many research areas such as human-computer interaction and computer vision. Hand gestures recognition requires the prior determination of the hand position through detection and tracking. One of the most efficient strategies for hand tracking is to use 2D visua information such as color and shape. However, visual-sensor-based hand tracking methods are very sensitive when tracking is performed under variable light conditions. Also, as hand movements are made in 3D space, the recognition performance of hand gestures using 2D information is inherently limited. In this article, we propose a novel real-time 3D hand tracking method in depth space using a 3D depth sensor and employing Kalman filter. We detect hand candidates using motion clusters and predefined wave motion, and track hand locations using Kalman filter. To verify the effectiveness of the proposed method, we compare the performance of the proposed method with the visual-based method. Experimental results show that the performance of the proposed method out performs visual-based method.",
author = "Sangheon Park and Sunjin Yu and Joongrock Kim and Sungjin Kim and Lee, {Sang Youn}",
year = "2012",
month = "12",
day = "1",
doi = "10.1186/1687-6180-2012-36",
language = "English",
volume = "2012",
journal = "Eurasip Journal on Advances in Signal Processing",
issn = "1687-6172",
publisher = "Springer Publishing Company",
number = "1",

}

3D hand tracking using Kalman filter in depth space. / Park, Sangheon; Yu, Sunjin; Kim, Joongrock; Kim, Sungjin; Lee, Sang Youn.

In: Eurasip Journal on Advances in Signal Processing, Vol. 2012, No. 1, 36, 01.12.2012.

Research output: Contribution to journalArticle

TY - JOUR

T1 - 3D hand tracking using Kalman filter in depth space

AU - Park, Sangheon

AU - Yu, Sunjin

AU - Kim, Joongrock

AU - Kim, Sungjin

AU - Lee, Sang Youn

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Hand gestures are an important type of natural language used in many research areas such as human-computer interaction and computer vision. Hand gestures recognition requires the prior determination of the hand position through detection and tracking. One of the most efficient strategies for hand tracking is to use 2D visua information such as color and shape. However, visual-sensor-based hand tracking methods are very sensitive when tracking is performed under variable light conditions. Also, as hand movements are made in 3D space, the recognition performance of hand gestures using 2D information is inherently limited. In this article, we propose a novel real-time 3D hand tracking method in depth space using a 3D depth sensor and employing Kalman filter. We detect hand candidates using motion clusters and predefined wave motion, and track hand locations using Kalman filter. To verify the effectiveness of the proposed method, we compare the performance of the proposed method with the visual-based method. Experimental results show that the performance of the proposed method out performs visual-based method.

AB - Hand gestures are an important type of natural language used in many research areas such as human-computer interaction and computer vision. Hand gestures recognition requires the prior determination of the hand position through detection and tracking. One of the most efficient strategies for hand tracking is to use 2D visua information such as color and shape. However, visual-sensor-based hand tracking methods are very sensitive when tracking is performed under variable light conditions. Also, as hand movements are made in 3D space, the recognition performance of hand gestures using 2D information is inherently limited. In this article, we propose a novel real-time 3D hand tracking method in depth space using a 3D depth sensor and employing Kalman filter. We detect hand candidates using motion clusters and predefined wave motion, and track hand locations using Kalman filter. To verify the effectiveness of the proposed method, we compare the performance of the proposed method with the visual-based method. Experimental results show that the performance of the proposed method out performs visual-based method.

UR - http://www.scopus.com/inward/record.url?scp=84864987169&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864987169&partnerID=8YFLogxK

U2 - 10.1186/1687-6180-2012-36

DO - 10.1186/1687-6180-2012-36

M3 - Article

AN - SCOPUS:84864987169

VL - 2012

JO - Eurasip Journal on Advances in Signal Processing

JF - Eurasip Journal on Advances in Signal Processing

SN - 1687-6172

IS - 1

M1 - 36

ER -