Remarks on a real-time, noncontact, nonwear, 3D human body posture estimation method

Kazuhiko Takahashi, Tatsumi Sakaguchi, Jun Ohya

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

This paper proposes a new real-time method of estimating human postures in three dimensions from trinocular images. The proposed method extracts feature points of the human body by analyzing contours of human silhouettes. The feature points are extracted by using the subtraction images when self-occlusions occur in the silhouette images. Dynamic compensation is carried out with a Kalman filter so that all feature points are tracked. The 3D coordinates of the feature points are reconstructed by considering the geometrical relationship between the three cameras. Experimental results confirm both the feasibility and the effectiveness of the proposed method.

Original languageEnglish
Pages (from-to)1-10
Number of pages10
JournalSystems and Computers in Japan
Volume31
Issue number14
DOIs
Publication statusPublished - 2000 Dec
Externally publishedYes

Fingerprint

Non-contact
Feature Point
Kalman filters
Cameras
Real-time
Silhouette
Subtraction
Occlusion
Kalman Filter
Three-dimension
Camera
Human
Compensation and Redress
Experimental Results

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Hardware and Architecture
  • Information Systems
  • Theoretical Computer Science

Cite this

Remarks on a real-time, noncontact, nonwear, 3D human body posture estimation method. / Takahashi, Kazuhiko; Sakaguchi, Tatsumi; Ohya, Jun.

In: Systems and Computers in Japan, Vol. 31, No. 14, 12.2000, p. 1-10.

Research output: Contribution to journalArticle

Takahashi, Kazuhiko ; Sakaguchi, Tatsumi ; Ohya, Jun. / Remarks on a real-time, noncontact, nonwear, 3D human body posture estimation method. In: Systems and Computers in Japan. 2000 ; Vol. 31, No. 14. pp. 1-10.
@article{c9625308926041fe8eb126a84413ac59,
title = "Remarks on a real-time, noncontact, nonwear, 3D human body posture estimation method",
abstract = "This paper proposes a new real-time method of estimating human postures in three dimensions from trinocular images. The proposed method extracts feature points of the human body by analyzing contours of human silhouettes. The feature points are extracted by using the subtraction images when self-occlusions occur in the silhouette images. Dynamic compensation is carried out with a Kalman filter so that all feature points are tracked. The 3D coordinates of the feature points are reconstructed by considering the geometrical relationship between the three cameras. Experimental results confirm both the feasibility and the effectiveness of the proposed method.",
author = "Kazuhiko Takahashi and Tatsumi Sakaguchi and Jun Ohya",
year = "2000",
month = "12",
doi = "10.1002/1520-684X(200012)31:14<1::AID-SCJ1>3.0.CO;2-0",
language = "English",
volume = "31",
pages = "1--10",
journal = "Systems and Computers in Japan",
issn = "0882-1666",
publisher = "John Wiley and Sons Inc.",
number = "14",

}

TY - JOUR

T1 - Remarks on a real-time, noncontact, nonwear, 3D human body posture estimation method

AU - Takahashi, Kazuhiko

AU - Sakaguchi, Tatsumi

AU - Ohya, Jun

PY - 2000/12

Y1 - 2000/12

N2 - This paper proposes a new real-time method of estimating human postures in three dimensions from trinocular images. The proposed method extracts feature points of the human body by analyzing contours of human silhouettes. The feature points are extracted by using the subtraction images when self-occlusions occur in the silhouette images. Dynamic compensation is carried out with a Kalman filter so that all feature points are tracked. The 3D coordinates of the feature points are reconstructed by considering the geometrical relationship between the three cameras. Experimental results confirm both the feasibility and the effectiveness of the proposed method.

AB - This paper proposes a new real-time method of estimating human postures in three dimensions from trinocular images. The proposed method extracts feature points of the human body by analyzing contours of human silhouettes. The feature points are extracted by using the subtraction images when self-occlusions occur in the silhouette images. Dynamic compensation is carried out with a Kalman filter so that all feature points are tracked. The 3D coordinates of the feature points are reconstructed by considering the geometrical relationship between the three cameras. Experimental results confirm both the feasibility and the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=0034504438&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034504438&partnerID=8YFLogxK

U2 - 10.1002/1520-684X(200012)31:14<1::AID-SCJ1>3.0.CO;2-0

DO - 10.1002/1520-684X(200012)31:14<1::AID-SCJ1>3.0.CO;2-0

M3 - Article

AN - SCOPUS:0034504438

VL - 31

SP - 1

EP - 10

JO - Systems and Computers in Japan

JF - Systems and Computers in Japan

SN - 0882-1666

IS - 14

ER -