Shape reconstruction of human foot from multi-camera images based on PCA of human shape database

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

Recently, researches and developments for measuring and modeling of human body are taking much attention. Our aim is to capture accurate shape of human foot, using 2D images acquired by multiple cameras, which can capture dynamic behavior of the object. In this paper, 3D active shape models is used for accurate reconstruction of surface shape of human foot. We apply principal component analysis (PCA) of human shape database, so that we can represent human's foot shape by approximately 12 principal component shapes. Because of the reduction of dimensions for representing the object shape, we can efficiently recover the object shape from multi-camera images, even though the object shape is partially occluded in some of input views. To demonstrate the proposed method, two kinds of experiments are presented: high accuracy reconstruction of human foot in a virtual reality environment with CG multi-camera images and in real world with eight CCD cameras. In those experiments, the recovered shape error with our method is around 2mm, while the error is around 4mm with volume intersection method.

Original languageEnglish
Title of host publicationProceedings of International Conference on 3-D Digital Imaging and Modeling, 3DIM
Pages424-431
Number of pages8
DOIs
Publication statusPublished - 2005
Event5th International Conference on 3-D Digital Imaging and Modeling, 3DIM 2005 - Ottawa, ON, Canada
Duration: 2005 Jun 132005 Jun 16

Other

Other5th International Conference on 3-D Digital Imaging and Modeling, 3DIM 2005
CountryCanada
CityOttawa, ON
Period05/6/1305/6/16

Fingerprint

Principal component analysis
Cameras
CCD cameras
Virtual reality
Experiments

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Wang, J., Saito, H., Kimura, M., Mochimaru, M., & Kanade, T. (2005). Shape reconstruction of human foot from multi-camera images based on PCA of human shape database. In Proceedings of International Conference on 3-D Digital Imaging and Modeling, 3DIM (pp. 424-431). [1443274] https://doi.org/10.1109/3DIM.2005.73

Shape reconstruction of human foot from multi-camera images based on PCA of human shape database. / Wang, Jiahui; Saito, Hideo; Kimura, Makoto; Mochimaru, Masaaki; Kanade, Takeo.

Proceedings of International Conference on 3-D Digital Imaging and Modeling, 3DIM. 2005. p. 424-431 1443274.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, J, Saito, H, Kimura, M, Mochimaru, M & Kanade, T 2005, Shape reconstruction of human foot from multi-camera images based on PCA of human shape database. in Proceedings of International Conference on 3-D Digital Imaging and Modeling, 3DIM., 1443274, pp. 424-431, 5th International Conference on 3-D Digital Imaging and Modeling, 3DIM 2005, Ottawa, ON, Canada, 05/6/13. https://doi.org/10.1109/3DIM.2005.73
Wang J, Saito H, Kimura M, Mochimaru M, Kanade T. Shape reconstruction of human foot from multi-camera images based on PCA of human shape database. In Proceedings of International Conference on 3-D Digital Imaging and Modeling, 3DIM. 2005. p. 424-431. 1443274 https://doi.org/10.1109/3DIM.2005.73
Wang, Jiahui ; Saito, Hideo ; Kimura, Makoto ; Mochimaru, Masaaki ; Kanade, Takeo. / Shape reconstruction of human foot from multi-camera images based on PCA of human shape database. Proceedings of International Conference on 3-D Digital Imaging and Modeling, 3DIM. 2005. pp. 424-431
@inproceedings{6a78e2b77eaf490d9412f4dd3e6ee8aa,
title = "Shape reconstruction of human foot from multi-camera images based on PCA of human shape database",
abstract = "Recently, researches and developments for measuring and modeling of human body are taking much attention. Our aim is to capture accurate shape of human foot, using 2D images acquired by multiple cameras, which can capture dynamic behavior of the object. In this paper, 3D active shape models is used for accurate reconstruction of surface shape of human foot. We apply principal component analysis (PCA) of human shape database, so that we can represent human's foot shape by approximately 12 principal component shapes. Because of the reduction of dimensions for representing the object shape, we can efficiently recover the object shape from multi-camera images, even though the object shape is partially occluded in some of input views. To demonstrate the proposed method, two kinds of experiments are presented: high accuracy reconstruction of human foot in a virtual reality environment with CG multi-camera images and in real world with eight CCD cameras. In those experiments, the recovered shape error with our method is around 2mm, while the error is around 4mm with volume intersection method.",
author = "Jiahui Wang and Hideo Saito and Makoto Kimura and Masaaki Mochimaru and Takeo Kanade",
year = "2005",
doi = "10.1109/3DIM.2005.73",
language = "English",
isbn = "0769523277",
pages = "424--431",
booktitle = "Proceedings of International Conference on 3-D Digital Imaging and Modeling, 3DIM",

}

TY - GEN

T1 - Shape reconstruction of human foot from multi-camera images based on PCA of human shape database

AU - Wang, Jiahui

AU - Saito, Hideo

AU - Kimura, Makoto

AU - Mochimaru, Masaaki

AU - Kanade, Takeo

PY - 2005

Y1 - 2005

N2 - Recently, researches and developments for measuring and modeling of human body are taking much attention. Our aim is to capture accurate shape of human foot, using 2D images acquired by multiple cameras, which can capture dynamic behavior of the object. In this paper, 3D active shape models is used for accurate reconstruction of surface shape of human foot. We apply principal component analysis (PCA) of human shape database, so that we can represent human's foot shape by approximately 12 principal component shapes. Because of the reduction of dimensions for representing the object shape, we can efficiently recover the object shape from multi-camera images, even though the object shape is partially occluded in some of input views. To demonstrate the proposed method, two kinds of experiments are presented: high accuracy reconstruction of human foot in a virtual reality environment with CG multi-camera images and in real world with eight CCD cameras. In those experiments, the recovered shape error with our method is around 2mm, while the error is around 4mm with volume intersection method.

AB - Recently, researches and developments for measuring and modeling of human body are taking much attention. Our aim is to capture accurate shape of human foot, using 2D images acquired by multiple cameras, which can capture dynamic behavior of the object. In this paper, 3D active shape models is used for accurate reconstruction of surface shape of human foot. We apply principal component analysis (PCA) of human shape database, so that we can represent human's foot shape by approximately 12 principal component shapes. Because of the reduction of dimensions for representing the object shape, we can efficiently recover the object shape from multi-camera images, even though the object shape is partially occluded in some of input views. To demonstrate the proposed method, two kinds of experiments are presented: high accuracy reconstruction of human foot in a virtual reality environment with CG multi-camera images and in real world with eight CCD cameras. In those experiments, the recovered shape error with our method is around 2mm, while the error is around 4mm with volume intersection method.

UR - http://www.scopus.com/inward/record.url?scp=33646784071&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646784071&partnerID=8YFLogxK

U2 - 10.1109/3DIM.2005.73

DO - 10.1109/3DIM.2005.73

M3 - Conference contribution

AN - SCOPUS:33646784071

SN - 0769523277

SN - 9780769523279

SP - 424

EP - 431

BT - Proceedings of International Conference on 3-D Digital Imaging and Modeling, 3DIM

ER -