A Model Based Estimation Method of Rigid and Non-rigid Face Motion for Artificial Reality

Juho LEE; Hyun Seung YANG

doi:10.1093/ietisy/e89-d.1.20

A Model Based Estimation Method of Rigid and Non-rigid Face Motion for Artificial Reality

Juho LEE, Hyun Seung YANG

Full Text Views

0

Cite this

Summary :

Face motion is composed of rigid motion and non-rigid motion. The rigid motion occurs from movements of the human head and the non-rigid motion derives from human's facial expression. In this paper, we present a technique for estimating these rigid/non-rigid motions of the human face simultaneously. First, we test whether the face motion is rigid. If it is rigid motion, we estimate the translation and rotation parameters over image sequences. Otherwise, the non-rigid motion parameters based on the spring-mass-damper (SMD) model are estimated using optical flow. We separate the rigid motion parameters explicitly from the non-rigid parameters for parameters de-coupling, so that we can achieve the face motion estimation more accurately and more efficiently. We will describe the details of our methods and show their efficacy with experiments.

Publication: IEICE TRANSACTIONS on Information Vol.E89-D No.1 pp.20-27

Publication Date: 2006/01/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e89-d.1.20

Type of Manuscript: Special Section PAPER (Special Section on Artificial Reality and Telexistence)

Category

Cite this

Copy

Juho LEE, Hyun Seung YANG, "A Model Based Estimation Method of Rigid and Non-rigid Face Motion for Artificial Reality" in IEICE TRANSACTIONS on Information, vol. E89-D, no. 1, pp. 20-27, January 2006, doi: 10.1093/ietisy/e89-d.1.20.
Abstract: Face motion is composed of rigid motion and non-rigid motion. The rigid motion occurs from movements of the human head and the non-rigid motion derives from human's facial expression. In this paper, we present a technique for estimating these rigid/non-rigid motions of the human face simultaneously. First, we test whether the face motion is rigid. If it is rigid motion, we estimate the translation and rotation parameters over image sequences. Otherwise, the non-rigid motion parameters based on the spring-mass-damper (SMD) model are estimated using optical flow. We separate the rigid motion parameters explicitly from the non-rigid parameters for parameters de-coupling, so that we can achieve the face motion estimation more accurately and more efficiently. We will describe the details of our methods and show their efficacy with experiments.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.1.20/_p

Copy

@ARTICLE{e89-d_1_20,
author={Juho LEE, Hyun Seung YANG, },
journal={IEICE TRANSACTIONS on Information},
title={A Model Based Estimation Method of Rigid and Non-rigid Face Motion for Artificial Reality},
year={2006},
volume={E89-D},
number={1},
pages={20-27},
abstract={Face motion is composed of rigid motion and non-rigid motion. The rigid motion occurs from movements of the human head and the non-rigid motion derives from human's facial expression. In this paper, we present a technique for estimating these rigid/non-rigid motions of the human face simultaneously. First, we test whether the face motion is rigid. If it is rigid motion, we estimate the translation and rotation parameters over image sequences. Otherwise, the non-rigid motion parameters based on the spring-mass-damper (SMD) model are estimated using optical flow. We separate the rigid motion parameters explicitly from the non-rigid parameters for parameters de-coupling, so that we can achieve the face motion estimation more accurately and more efficiently. We will describe the details of our methods and show their efficacy with experiments.},
keywords={},
doi={10.1093/ietisy/e89-d.1.20},
ISSN={1745-1361},
month={January},}

Copy

TY - JOUR
TI - A Model Based Estimation Method of Rigid and Non-rigid Face Motion for Artificial Reality
T2 - IEICE TRANSACTIONS on Information
SP - 20
EP - 27
AU - Juho LEE
AU - Hyun Seung YANG
PY - 2006
DO - 10.1093/ietisy/e89-d.1.20
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2006
AB - Face motion is composed of rigid motion and non-rigid motion. The rigid motion occurs from movements of the human head and the non-rigid motion derives from human's facial expression. In this paper, we present a technique for estimating these rigid/non-rigid motions of the human face simultaneously. First, we test whether the face motion is rigid. If it is rigid motion, we estimate the translation and rotation parameters over image sequences. Otherwise, the non-rigid motion parameters based on the spring-mass-damper (SMD) model are estimated using optical flow. We separate the rigid motion parameters explicitly from the non-rigid parameters for parameters de-coupling, so that we can achieve the face motion estimation more accurately and more efficiently. We will describe the details of our methods and show their efficacy with experiments.
ER -