Image-based center of mass estimation of the human body via 3D shape and kinematic structure

Tomoya Kaichi; Shohei Mori; Hideo Saito; Kosuke Takahashi; Dan Mikami; Mariko Isogawa; Yoshinori Kusachi

doi:10.1007/s12283-019-0309-2

Image-based center of mass estimation of the human body via 3D shape and kinematic structure

Tomoya Kaichi, Shohei Mori, Hideo Saito, Kosuke Takahashi, Dan Mikami, Mariko Isogawa, Yoshinori Kusachi

Department of Information and Computer Science

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

Abstract

This paper presents a method to estimate a time-sequential trajectory of the center of mass (CoM) of an athlete from a multi-view set of cameras. Collecting the CoM typically requires large-scale measuring systems or attaching sensors to the athletes. To mitigate such hardware limitations, the present study takes a multi-view video-based approach. The proposed method reconstructs subjects’ voxels from a set of multi-view frames and weights each voxel with body part-dependent weights to calculate a CoM. Our results, using real data measured in a studio, showed that the proposed method can estimate CoM within 20 mm concerning center of pressure measures.

Original language	English
Article number	17
Journal	Sports Engineering
Volume	22
Issue number	3-4
DOIs	https://doi.org/10.1007/s12283-019-0309-2
Publication status	Published - 2019 Dec

Keywords

Center of mass
Multi-view human pose estimation
Multi-view videos
Visual hull

ASJC Scopus subject areas

Biomedical Engineering
Modelling and Simulation
Orthopedics and Sports Medicine
Physical Therapy, Sports Therapy and Rehabilitation
Mechanics of Materials
Mechanical Engineering

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/s12283-019-0309-2

Cite this

@article{98adf208d3b24e36ace9ad9fa2b85695,

title = "Image-based center of mass estimation of the human body via 3D shape and kinematic structure",

abstract = "This paper presents a method to estimate a time-sequential trajectory of the center of mass (CoM) of an athlete from a multi-view set of cameras. Collecting the CoM typically requires large-scale measuring systems or attaching sensors to the athletes. To mitigate such hardware limitations, the present study takes a multi-view video-based approach. The proposed method reconstructs subjects{\textquoteright} voxels from a set of multi-view frames and weights each voxel with body part-dependent weights to calculate a CoM. Our results, using real data measured in a studio, showed that the proposed method can estimate CoM within 20 mm concerning center of pressure measures.",

keywords = "Center of mass, Multi-view human pose estimation, Multi-view videos, Visual hull",

author = "Tomoya Kaichi and Shohei Mori and Hideo Saito and Kosuke Takahashi and Dan Mikami and Mariko Isogawa and Yoshinori Kusachi",

note = "Funding Information: This work was supported by Grant-in-Aid for JSPS Fellows (19J22153). Funding Information: This work was supported by Grant-in-Aid for JSPS Fellows (19J22153). Publisher Copyright: {\textcopyright} 2019, International Sports Engineering Association.",

year = "2019",

month = dec,

doi = "10.1007/s12283-019-0309-2",

language = "English",

volume = "22",

journal = "Sports Engineering",

issn = "1369-7072",

publisher = "Springer London",

number = "3-4",

}

TY - JOUR

T1 - Image-based center of mass estimation of the human body via 3D shape and kinematic structure

AU - Kaichi, Tomoya

AU - Mori, Shohei

AU - Saito, Hideo

AU - Takahashi, Kosuke

AU - Mikami, Dan

AU - Isogawa, Mariko

AU - Kusachi, Yoshinori

N1 - Funding Information: This work was supported by Grant-in-Aid for JSPS Fellows (19J22153). Funding Information: This work was supported by Grant-in-Aid for JSPS Fellows (19J22153). Publisher Copyright: © 2019, International Sports Engineering Association.

PY - 2019/12

Y1 - 2019/12

N2 - This paper presents a method to estimate a time-sequential trajectory of the center of mass (CoM) of an athlete from a multi-view set of cameras. Collecting the CoM typically requires large-scale measuring systems or attaching sensors to the athletes. To mitigate such hardware limitations, the present study takes a multi-view video-based approach. The proposed method reconstructs subjects’ voxels from a set of multi-view frames and weights each voxel with body part-dependent weights to calculate a CoM. Our results, using real data measured in a studio, showed that the proposed method can estimate CoM within 20 mm concerning center of pressure measures.

AB - This paper presents a method to estimate a time-sequential trajectory of the center of mass (CoM) of an athlete from a multi-view set of cameras. Collecting the CoM typically requires large-scale measuring systems or attaching sensors to the athletes. To mitigate such hardware limitations, the present study takes a multi-view video-based approach. The proposed method reconstructs subjects’ voxels from a set of multi-view frames and weights each voxel with body part-dependent weights to calculate a CoM. Our results, using real data measured in a studio, showed that the proposed method can estimate CoM within 20 mm concerning center of pressure measures.

KW - Center of mass

KW - Multi-view human pose estimation

KW - Multi-view videos

KW - Visual hull

UR - http://www.scopus.com/inward/record.url?scp=85070209989&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070209989&partnerID=8YFLogxK

U2 - 10.1007/s12283-019-0309-2

DO - 10.1007/s12283-019-0309-2

M3 - Article

AN - SCOPUS:85070209989

SN - 1369-7072

VL - 22

JO - Sports Engineering

JF - Sports Engineering

IS - 3-4

M1 - 17

ER -

Image-based center of mass estimation of the human body via 3D shape and kinematic structure

Abstract

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this