Remarks on a real-time 3d human body posture estimation method using trinocular images

Kazuhiko Takahashi, Tatsumi Sakaguchi, Jun Ohya

Research output: Chapter in Book/Report/Conference proceedingChapter

15 Citations (Scopus)

Abstract

This paper proposes a new real-time method of estimating human postures in 3D from trinocular images. The proposed method extracts feature points of the human body by applying a type of function analysis to contours of human silhouettes. To overcome self-occlusion problems, dynamic compensation is carried out using the Kalman filter and 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, and an application example of the 3D human body posture estimation to a motion recognition system is presented.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages693-697
Number of pages5
Volume15
Edition4
Publication statusPublished - 2000
Externally publishedYes

Fingerprint

Kalman filters
Cameras
Compensation and Redress

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

Cite this

Takahashi, K., Sakaguchi, T., & Ohya, J. (2000). Remarks on a real-time 3d human body posture estimation method using trinocular images. In Proceedings - International Conference on Pattern Recognition (4 ed., Vol. 15, pp. 693-697)

Remarks on a real-time 3d human body posture estimation method using trinocular images. / Takahashi, Kazuhiko; Sakaguchi, Tatsumi; Ohya, Jun.

Proceedings - International Conference on Pattern Recognition. Vol. 15 4. ed. 2000. p. 693-697.

Research output: Chapter in Book/Report/Conference proceedingChapter

Takahashi, K, Sakaguchi, T & Ohya, J 2000, Remarks on a real-time 3d human body posture estimation method using trinocular images. in Proceedings - International Conference on Pattern Recognition. 4 edn, vol. 15, pp. 693-697.
Takahashi K, Sakaguchi T, Ohya J. Remarks on a real-time 3d human body posture estimation method using trinocular images. In Proceedings - International Conference on Pattern Recognition. 4 ed. Vol. 15. 2000. p. 693-697
Takahashi, Kazuhiko ; Sakaguchi, Tatsumi ; Ohya, Jun. / Remarks on a real-time 3d human body posture estimation method using trinocular images. Proceedings - International Conference on Pattern Recognition. Vol. 15 4. ed. 2000. pp. 693-697
@inbook{22058baa469b44caa2a550f5a5eb9a7a,
title = "Remarks on a real-time 3d human body posture estimation method using trinocular images",
abstract = "This paper proposes a new real-time method of estimating human postures in 3D from trinocular images. The proposed method extracts feature points of the human body by applying a type of function analysis to contours of human silhouettes. To overcome self-occlusion problems, dynamic compensation is carried out using the Kalman filter and 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, and an application example of the 3D human body posture estimation to a motion recognition system is presented.",
author = "Kazuhiko Takahashi and Tatsumi Sakaguchi and Jun Ohya",
year = "2000",
language = "English",
volume = "15",
pages = "693--697",
booktitle = "Proceedings - International Conference on Pattern Recognition",
edition = "4",

}

TY - CHAP

T1 - Remarks on a real-time 3d human body posture estimation method using trinocular images

AU - Takahashi, Kazuhiko

AU - Sakaguchi, Tatsumi

AU - Ohya, Jun

PY - 2000

Y1 - 2000

N2 - This paper proposes a new real-time method of estimating human postures in 3D from trinocular images. The proposed method extracts feature points of the human body by applying a type of function analysis to contours of human silhouettes. To overcome self-occlusion problems, dynamic compensation is carried out using the Kalman filter and 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, and an application example of the 3D human body posture estimation to a motion recognition system is presented.

AB - This paper proposes a new real-time method of estimating human postures in 3D from trinocular images. The proposed method extracts feature points of the human body by applying a type of function analysis to contours of human silhouettes. To overcome self-occlusion problems, dynamic compensation is carried out using the Kalman filter and 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, and an application example of the 3D human body posture estimation to a motion recognition system is presented.

UR - http://www.scopus.com/inward/record.url?scp=0006669393&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0006669393&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:0006669393

VL - 15

SP - 693

EP - 697

BT - Proceedings - International Conference on Pattern Recognition

ER -