Model-based hand tracking by chamfer distance and adaptive color learning using particle filter

Chutisant Kerdvibulvech, Hideo Saito

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

We propose a new model-based hand tracking method for recovering of three-dimensional hand motion from an image sequence. We first build a three-dimensional hand model using truncated quadrics. The degrees of freedom (DOF) for each joint correspond to the DOF of a real hand. This feature extraction is performed by using the Chamfer Distance function for the edge likelihood. The silhouette likelihood is performed by using a Bayesian classifier and the online adaptation of skin color probabilities. Therefore, it is to effectively deal with any illumination changes. Particle filtering is used to track the hand by predicting the next state of three-dimensional hand model. By using these techniques, this method adds the useful ability of automatic recovery from tracking failures. This method can also be used to track the guitarist's hand.

Original languageEnglish
Article number724947
JournalEurasip Journal on Image and Video Processing
Volume2009
DOIs
Publication statusPublished - 2009

Fingerprint

Color
Feature extraction
Skin
Classifiers
Lighting
Recovery

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Information Systems

Cite this

Model-based hand tracking by chamfer distance and adaptive color learning using particle filter. / Kerdvibulvech, Chutisant; Saito, Hideo.

In: Eurasip Journal on Image and Video Processing, Vol. 2009, 724947, 2009.

Research output: Contribution to journalArticle

@article{217d3abcbe0246e18e4e41d7103e6ecb,
title = "Model-based hand tracking by chamfer distance and adaptive color learning using particle filter",
abstract = "We propose a new model-based hand tracking method for recovering of three-dimensional hand motion from an image sequence. We first build a three-dimensional hand model using truncated quadrics. The degrees of freedom (DOF) for each joint correspond to the DOF of a real hand. This feature extraction is performed by using the Chamfer Distance function for the edge likelihood. The silhouette likelihood is performed by using a Bayesian classifier and the online adaptation of skin color probabilities. Therefore, it is to effectively deal with any illumination changes. Particle filtering is used to track the hand by predicting the next state of three-dimensional hand model. By using these techniques, this method adds the useful ability of automatic recovery from tracking failures. This method can also be used to track the guitarist's hand.",
author = "Chutisant Kerdvibulvech and Hideo Saito",
year = "2009",
doi = "10.1155/2009/724947",
language = "English",
volume = "2009",
journal = "Eurasip Journal on Image and Video Processing",
issn = "1687-5176",
publisher = "Springer Publishing Company",

}

TY - JOUR

T1 - Model-based hand tracking by chamfer distance and adaptive color learning using particle filter

AU - Kerdvibulvech, Chutisant

AU - Saito, Hideo

PY - 2009

Y1 - 2009

N2 - We propose a new model-based hand tracking method for recovering of three-dimensional hand motion from an image sequence. We first build a three-dimensional hand model using truncated quadrics. The degrees of freedom (DOF) for each joint correspond to the DOF of a real hand. This feature extraction is performed by using the Chamfer Distance function for the edge likelihood. The silhouette likelihood is performed by using a Bayesian classifier and the online adaptation of skin color probabilities. Therefore, it is to effectively deal with any illumination changes. Particle filtering is used to track the hand by predicting the next state of three-dimensional hand model. By using these techniques, this method adds the useful ability of automatic recovery from tracking failures. This method can also be used to track the guitarist's hand.

AB - We propose a new model-based hand tracking method for recovering of three-dimensional hand motion from an image sequence. We first build a three-dimensional hand model using truncated quadrics. The degrees of freedom (DOF) for each joint correspond to the DOF of a real hand. This feature extraction is performed by using the Chamfer Distance function for the edge likelihood. The silhouette likelihood is performed by using a Bayesian classifier and the online adaptation of skin color probabilities. Therefore, it is to effectively deal with any illumination changes. Particle filtering is used to track the hand by predicting the next state of three-dimensional hand model. By using these techniques, this method adds the useful ability of automatic recovery from tracking failures. This method can also be used to track the guitarist's hand.

UR - http://www.scopus.com/inward/record.url?scp=74849115623&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=74849115623&partnerID=8YFLogxK

U2 - 10.1155/2009/724947

DO - 10.1155/2009/724947

M3 - Article

AN - SCOPUS:74849115623

VL - 2009

JO - Eurasip Journal on Image and Video Processing

JF - Eurasip Journal on Image and Video Processing

SN - 1687-5176

M1 - 724947

ER -