Robust pose estimation for human body hidden with a cover using body shape feature obtained by normal vector

Yuta Kudo, Takehiko Sashida, Yoshimitsu Aoki

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we present a robust pose estimation method of a human body hidden with a cover. Our goal is an automatically monitoring system of sleeping human using noncontact and noninvasive sensors for elderly care. We propose a new method for robust human pose estimation from a single depth image using human body shape ITXXICI constructed by nonnal vector infonnation. This shape model is able to represent shapes of rough body, and is effective in robust pose estimation for a person who placed iiiton and blanket. In our method, first, head position is detected from a depth image using SVM. Then, body region is detected by comparing human body sliape model. Head position is used as initial position of body region detecting. Body region is composed of many small rectangles. Next, body region is divided into three body parts by distance between parts. Finally, each part pose is detennined by a linear estimation using point clouds of right and left of the rectangle in each body region.

Original languageEnglish
Pages (from-to)1166-1175
Number of pages10
JournalSeimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering
Volume80
Issue number12
DOIs
Publication statusPublished - 2014 Dec 1
Externally publishedYes

Fingerprint

Monitoring
Sensors

Keywords

  • 3D image
  • Covered body pose estimation
  • Monitoring system
  • Oriented nonnal vector
  • Pose estimation

ASJC Scopus subject areas

  • Mechanical Engineering

Cite this

@article{db07b9087cdc4a83b24f2eef9bd2f3dc,
title = "Robust pose estimation for human body hidden with a cover using body shape feature obtained by normal vector",
abstract = "In this paper, we present a robust pose estimation method of a human body hidden with a cover. Our goal is an automatically monitoring system of sleeping human using noncontact and noninvasive sensors for elderly care. We propose a new method for robust human pose estimation from a single depth image using human body shape ITXXICI constructed by nonnal vector infonnation. This shape model is able to represent shapes of rough body, and is effective in robust pose estimation for a person who placed iiiton and blanket. In our method, first, head position is detected from a depth image using SVM. Then, body region is detected by comparing human body sliape model. Head position is used as initial position of body region detecting. Body region is composed of many small rectangles. Next, body region is divided into three body parts by distance between parts. Finally, each part pose is detennined by a linear estimation using point clouds of right and left of the rectangle in each body region.",
keywords = "3D image, Covered body pose estimation, Monitoring system, Oriented nonnal vector, Pose estimation",
author = "Yuta Kudo and Takehiko Sashida and Yoshimitsu Aoki",
year = "2014",
month = "12",
day = "1",
doi = "10.2493/jjspe.80.1166",
language = "English",
volume = "80",
pages = "1166--1175",
journal = "Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering",
issn = "0912-0289",
publisher = "Japan Society for Precision Engineering",
number = "12",

}

TY - JOUR

T1 - Robust pose estimation for human body hidden with a cover using body shape feature obtained by normal vector

AU - Kudo, Yuta

AU - Sashida, Takehiko

AU - Aoki, Yoshimitsu

PY - 2014/12/1

Y1 - 2014/12/1

N2 - In this paper, we present a robust pose estimation method of a human body hidden with a cover. Our goal is an automatically monitoring system of sleeping human using noncontact and noninvasive sensors for elderly care. We propose a new method for robust human pose estimation from a single depth image using human body shape ITXXICI constructed by nonnal vector infonnation. This shape model is able to represent shapes of rough body, and is effective in robust pose estimation for a person who placed iiiton and blanket. In our method, first, head position is detected from a depth image using SVM. Then, body region is detected by comparing human body sliape model. Head position is used as initial position of body region detecting. Body region is composed of many small rectangles. Next, body region is divided into three body parts by distance between parts. Finally, each part pose is detennined by a linear estimation using point clouds of right and left of the rectangle in each body region.

AB - In this paper, we present a robust pose estimation method of a human body hidden with a cover. Our goal is an automatically monitoring system of sleeping human using noncontact and noninvasive sensors for elderly care. We propose a new method for robust human pose estimation from a single depth image using human body shape ITXXICI constructed by nonnal vector infonnation. This shape model is able to represent shapes of rough body, and is effective in robust pose estimation for a person who placed iiiton and blanket. In our method, first, head position is detected from a depth image using SVM. Then, body region is detected by comparing human body sliape model. Head position is used as initial position of body region detecting. Body region is composed of many small rectangles. Next, body region is divided into three body parts by distance between parts. Finally, each part pose is detennined by a linear estimation using point clouds of right and left of the rectangle in each body region.

KW - 3D image

KW - Covered body pose estimation

KW - Monitoring system

KW - Oriented nonnal vector

KW - Pose estimation

UR - http://www.scopus.com/inward/record.url?scp=84931421441&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84931421441&partnerID=8YFLogxK

U2 - 10.2493/jjspe.80.1166

DO - 10.2493/jjspe.80.1166

M3 - Article

AN - SCOPUS:84931421441

VL - 80

SP - 1166

EP - 1175

JO - Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering

JF - Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering

SN - 0912-0289

IS - 12

ER -