PCA-based 3D shape reconstruction of human foot using multiple viewpoint cameras

Edmée Amstutz, Tomoaki Teshima, Makoto Kimura, Masaaki Mochimaru, Hideo Saito

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

This paper describes a multiple camera-based method to reconstruct the 3D shape of a human foot. From a foot database, an initial 3D model of the foot represented by a cloud of points is built. The shape parameters, which can characterize more than 92% of a foot, are defined by using the principal component analysis method. Then, using "active shape models", the initial 3D model is adapted to the real foot captured in multiple images by applying some constraints (edge points' distance and color variance). We insist here on the experiment part where we demonstrate the efficiency of the proposed method on a plastic foot model, and also on real human feet with various shapes. We propose and compare different ways of texturing the foot which is needed for reconstruction. We present an experiment performed on the plastic foot model and on human feet and propose two different ways to improve the final 3D shape's accuracy according to the previous experiments' results. The first improvement proposed is the densification of the cloud of points used to represent the initial model and the foot database. The second improvement concerns the projected patterns used to texture the foot. We conclude by showing the obtained results for a human foot with the average computed shape error being only 1.06 mm.

Original languageEnglish
Pages (from-to)217-225
Number of pages9
JournalInternational Journal of Automation and Computing
Volume5
Issue number3
DOIs
Publication statusPublished - 2008 Jul

Fingerprint

Shape Reconstruction
3D shape
3D Reconstruction
Camera
Cameras
3D Model
Plastics
Active Shape Model
Experiment
Shape Parameter
Principal Component Analysis
Texture
Texturing
Experiments
Model
Densification
Principal component analysis
Human
Textures
Demonstrate

Keywords

  • 3D reconstruction from multiview cameras
  • Principal component analysis
  • Shape measurement

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Applied Mathematics
  • Modelling and Simulation

Cite this

PCA-based 3D shape reconstruction of human foot using multiple viewpoint cameras. / Amstutz, Edmée; Teshima, Tomoaki; Kimura, Makoto; Mochimaru, Masaaki; Saito, Hideo.

In: International Journal of Automation and Computing, Vol. 5, No. 3, 07.2008, p. 217-225.

Research output: Contribution to journalArticle

Amstutz, Edmée ; Teshima, Tomoaki ; Kimura, Makoto ; Mochimaru, Masaaki ; Saito, Hideo. / PCA-based 3D shape reconstruction of human foot using multiple viewpoint cameras. In: International Journal of Automation and Computing. 2008 ; Vol. 5, No. 3. pp. 217-225.
@article{62b89cf590a742d1943507426ec0a065,
title = "PCA-based 3D shape reconstruction of human foot using multiple viewpoint cameras",
abstract = "This paper describes a multiple camera-based method to reconstruct the 3D shape of a human foot. From a foot database, an initial 3D model of the foot represented by a cloud of points is built. The shape parameters, which can characterize more than 92{\%} of a foot, are defined by using the principal component analysis method. Then, using {"}active shape models{"}, the initial 3D model is adapted to the real foot captured in multiple images by applying some constraints (edge points' distance and color variance). We insist here on the experiment part where we demonstrate the efficiency of the proposed method on a plastic foot model, and also on real human feet with various shapes. We propose and compare different ways of texturing the foot which is needed for reconstruction. We present an experiment performed on the plastic foot model and on human feet and propose two different ways to improve the final 3D shape's accuracy according to the previous experiments' results. The first improvement proposed is the densification of the cloud of points used to represent the initial model and the foot database. The second improvement concerns the projected patterns used to texture the foot. We conclude by showing the obtained results for a human foot with the average computed shape error being only 1.06 mm.",
keywords = "3D reconstruction from multiview cameras, Principal component analysis, Shape measurement",
author = "Edm{\'e}e Amstutz and Tomoaki Teshima and Makoto Kimura and Masaaki Mochimaru and Hideo Saito",
year = "2008",
month = "7",
doi = "10.1007/s11633-008-0217-6",
language = "English",
volume = "5",
pages = "217--225",
journal = "International Journal of Automation and Computing",
issn = "1476-8186",
publisher = "Chinese Academy of Sciences",
number = "3",

}

TY - JOUR

T1 - PCA-based 3D shape reconstruction of human foot using multiple viewpoint cameras

AU - Amstutz, Edmée

AU - Teshima, Tomoaki

AU - Kimura, Makoto

AU - Mochimaru, Masaaki

AU - Saito, Hideo

PY - 2008/7

Y1 - 2008/7

N2 - This paper describes a multiple camera-based method to reconstruct the 3D shape of a human foot. From a foot database, an initial 3D model of the foot represented by a cloud of points is built. The shape parameters, which can characterize more than 92% of a foot, are defined by using the principal component analysis method. Then, using "active shape models", the initial 3D model is adapted to the real foot captured in multiple images by applying some constraints (edge points' distance and color variance). We insist here on the experiment part where we demonstrate the efficiency of the proposed method on a plastic foot model, and also on real human feet with various shapes. We propose and compare different ways of texturing the foot which is needed for reconstruction. We present an experiment performed on the plastic foot model and on human feet and propose two different ways to improve the final 3D shape's accuracy according to the previous experiments' results. The first improvement proposed is the densification of the cloud of points used to represent the initial model and the foot database. The second improvement concerns the projected patterns used to texture the foot. We conclude by showing the obtained results for a human foot with the average computed shape error being only 1.06 mm.

AB - This paper describes a multiple camera-based method to reconstruct the 3D shape of a human foot. From a foot database, an initial 3D model of the foot represented by a cloud of points is built. The shape parameters, which can characterize more than 92% of a foot, are defined by using the principal component analysis method. Then, using "active shape models", the initial 3D model is adapted to the real foot captured in multiple images by applying some constraints (edge points' distance and color variance). We insist here on the experiment part where we demonstrate the efficiency of the proposed method on a plastic foot model, and also on real human feet with various shapes. We propose and compare different ways of texturing the foot which is needed for reconstruction. We present an experiment performed on the plastic foot model and on human feet and propose two different ways to improve the final 3D shape's accuracy according to the previous experiments' results. The first improvement proposed is the densification of the cloud of points used to represent the initial model and the foot database. The second improvement concerns the projected patterns used to texture the foot. We conclude by showing the obtained results for a human foot with the average computed shape error being only 1.06 mm.

KW - 3D reconstruction from multiview cameras

KW - Principal component analysis

KW - Shape measurement

UR - http://www.scopus.com/inward/record.url?scp=47249124493&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47249124493&partnerID=8YFLogxK

U2 - 10.1007/s11633-008-0217-6

DO - 10.1007/s11633-008-0217-6

M3 - Article

AN - SCOPUS:47249124493

VL - 5

SP - 217

EP - 225

JO - International Journal of Automation and Computing

JF - International Journal of Automation and Computing

SN - 1476-8186

IS - 3

ER -