Human foot reconstruction from multiple camera images with foot shape database

Jiahui Wang, Hideo Saito, Makoto Kimura, Masaaki Mochimarl, Takeo Kanade

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Recently, researches and developments for measuring and modeling of the human body have been receiving much attention. Our aim is to reconstruct an accurate shape of a human foot from multiple camera images, which can capture dynamic behavior of the object. In this paper, a foot-shape database is used for accurate reconstruction of human foot. By using Principal Component Analysis, the foot shape can be represented with new meaningful variables. The dimensionality of the data is also reduced. Thus, the shape of object can be recovered efficiently, even though the object is partially occluded in some input views. To demonstrate the proposed method, two kinds of experiments are presented: reconstruction of human foot in a virtual reality environment with CG multi-camera images, and in real world with eight CCD cameras. In the experiments, the reconstructed shape error with our method is around 2 mm in average, while the error is more than 4mm with conventional volume intersection method.

Original languageEnglish
Pages (from-to)1732-1741
Number of pages10
JournalIEICE Transactions on Information and Systems
VolumeE89-D
Issue number5
DOIs
Publication statusPublished - 2006 May

Fingerprint

Cameras
CCD cameras
Principal component analysis
Virtual reality
Experiments

Keywords

  • Anthropometry
  • Deformable model
  • Multiple cameras
  • Principal component analysis
  • Shape reconstruction

ASJC Scopus subject areas

  • Information Systems
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Human foot reconstruction from multiple camera images with foot shape database. / Wang, Jiahui; Saito, Hideo; Kimura, Makoto; Mochimarl, Masaaki; Kanade, Takeo.

In: IEICE Transactions on Information and Systems, Vol. E89-D, No. 5, 05.2006, p. 1732-1741.

Research output: Contribution to journalArticle

Wang, Jiahui ; Saito, Hideo ; Kimura, Makoto ; Mochimarl, Masaaki ; Kanade, Takeo. / Human foot reconstruction from multiple camera images with foot shape database. In: IEICE Transactions on Information and Systems. 2006 ; Vol. E89-D, No. 5. pp. 1732-1741.
@article{eda4597080ce4275a1eb6aae4aa7b747,
title = "Human foot reconstruction from multiple camera images with foot shape database",
abstract = "Recently, researches and developments for measuring and modeling of the human body have been receiving much attention. Our aim is to reconstruct an accurate shape of a human foot from multiple camera images, which can capture dynamic behavior of the object. In this paper, a foot-shape database is used for accurate reconstruction of human foot. By using Principal Component Analysis, the foot shape can be represented with new meaningful variables. The dimensionality of the data is also reduced. Thus, the shape of object can be recovered efficiently, even though the object is partially occluded in some input views. To demonstrate the proposed method, two kinds of experiments are presented: reconstruction of human foot in a virtual reality environment with CG multi-camera images, and in real world with eight CCD cameras. In the experiments, the reconstructed shape error with our method is around 2 mm in average, while the error is more than 4mm with conventional volume intersection method.",
keywords = "Anthropometry, Deformable model, Multiple cameras, Principal component analysis, Shape reconstruction",
author = "Jiahui Wang and Hideo Saito and Makoto Kimura and Masaaki Mochimarl and Takeo Kanade",
year = "2006",
month = "5",
doi = "10.1093/ietisy/e89-d.5.1732",
language = "English",
volume = "E89-D",
pages = "1732--1741",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "5",

}

TY - JOUR

T1 - Human foot reconstruction from multiple camera images with foot shape database

AU - Wang, Jiahui

AU - Saito, Hideo

AU - Kimura, Makoto

AU - Mochimarl, Masaaki

AU - Kanade, Takeo

PY - 2006/5

Y1 - 2006/5

N2 - Recently, researches and developments for measuring and modeling of the human body have been receiving much attention. Our aim is to reconstruct an accurate shape of a human foot from multiple camera images, which can capture dynamic behavior of the object. In this paper, a foot-shape database is used for accurate reconstruction of human foot. By using Principal Component Analysis, the foot shape can be represented with new meaningful variables. The dimensionality of the data is also reduced. Thus, the shape of object can be recovered efficiently, even though the object is partially occluded in some input views. To demonstrate the proposed method, two kinds of experiments are presented: reconstruction of human foot in a virtual reality environment with CG multi-camera images, and in real world with eight CCD cameras. In the experiments, the reconstructed shape error with our method is around 2 mm in average, while the error is more than 4mm with conventional volume intersection method.

AB - Recently, researches and developments for measuring and modeling of the human body have been receiving much attention. Our aim is to reconstruct an accurate shape of a human foot from multiple camera images, which can capture dynamic behavior of the object. In this paper, a foot-shape database is used for accurate reconstruction of human foot. By using Principal Component Analysis, the foot shape can be represented with new meaningful variables. The dimensionality of the data is also reduced. Thus, the shape of object can be recovered efficiently, even though the object is partially occluded in some input views. To demonstrate the proposed method, two kinds of experiments are presented: reconstruction of human foot in a virtual reality environment with CG multi-camera images, and in real world with eight CCD cameras. In the experiments, the reconstructed shape error with our method is around 2 mm in average, while the error is more than 4mm with conventional volume intersection method.

KW - Anthropometry

KW - Deformable model

KW - Multiple cameras

KW - Principal component analysis

KW - Shape reconstruction

UR - http://www.scopus.com/inward/record.url?scp=33646763855&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646763855&partnerID=8YFLogxK

U2 - 10.1093/ietisy/e89-d.5.1732

DO - 10.1093/ietisy/e89-d.5.1732

M3 - Article

VL - E89-D

SP - 1732

EP - 1741

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 5

ER -