Human body postures from trinocular camera images

Shoichiro Iwasawa, Jun Ohya, Kazuhiko Takahashi, Tatsumi Sakaguchi, Kazuyuki Ebihara, Shigeo Morishima

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

15 Citations (Scopus)

Abstract

This paper proposes a new real-time method for estimating human postures in 3D from trinocular images. In this method, an upper body orientation detection and a heuristic contour analysis are performed on the human silhouettes extracted from the trinocular images so that representative points such as the top of the head can be located. The major joint positions are estimated based on a genetic algorithm-based learning procedure. 3D coordinates of the representative points and joints are then obtained from the two views by evaluating the appropriateness of the three views. The proposed method implemented on a personal computer runs in real-time. Experimental results show high estimation accuracies and the effectiveness of the view selection process.

Original languageEnglish
Title of host publicationProceedings - 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000
PublisherIEEE Computer Society
Pages326-331
Number of pages6
ISBN (Print)0769505805, 9780769505800
DOIs
Publication statusPublished - 2000
Externally publishedYes
Event4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000 - Grenoble
Duration: 2000 Mar 282000 Mar 30

Other

Other4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000
CityGrenoble
Period00/3/2800/3/30

Fingerprint

Personal computers
Genetic algorithms
Cameras

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Iwasawa, S., Ohya, J., Takahashi, K., Sakaguchi, T., Ebihara, K., & Morishima, S. (2000). Human body postures from trinocular camera images. In Proceedings - 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000 (pp. 326-331). [840654] IEEE Computer Society. https://doi.org/10.1109/AFGR.2000.840654

Human body postures from trinocular camera images. / Iwasawa, Shoichiro; Ohya, Jun; Takahashi, Kazuhiko; Sakaguchi, Tatsumi; Ebihara, Kazuyuki; Morishima, Shigeo.

Proceedings - 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000. IEEE Computer Society, 2000. p. 326-331 840654.

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

Iwasawa, S, Ohya, J, Takahashi, K, Sakaguchi, T, Ebihara, K & Morishima, S 2000, Human body postures from trinocular camera images. in Proceedings - 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000., 840654, IEEE Computer Society, pp. 326-331, 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000, Grenoble, 00/3/28. https://doi.org/10.1109/AFGR.2000.840654
Iwasawa S, Ohya J, Takahashi K, Sakaguchi T, Ebihara K, Morishima S. Human body postures from trinocular camera images. In Proceedings - 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000. IEEE Computer Society. 2000. p. 326-331. 840654 https://doi.org/10.1109/AFGR.2000.840654
Iwasawa, Shoichiro ; Ohya, Jun ; Takahashi, Kazuhiko ; Sakaguchi, Tatsumi ; Ebihara, Kazuyuki ; Morishima, Shigeo. / Human body postures from trinocular camera images. Proceedings - 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000. IEEE Computer Society, 2000. pp. 326-331
@inproceedings{899f5733486146f5a31c134921ae53b0,
title = "Human body postures from trinocular camera images",
abstract = "This paper proposes a new real-time method for estimating human postures in 3D from trinocular images. In this method, an upper body orientation detection and a heuristic contour analysis are performed on the human silhouettes extracted from the trinocular images so that representative points such as the top of the head can be located. The major joint positions are estimated based on a genetic algorithm-based learning procedure. 3D coordinates of the representative points and joints are then obtained from the two views by evaluating the appropriateness of the three views. The proposed method implemented on a personal computer runs in real-time. Experimental results show high estimation accuracies and the effectiveness of the view selection process.",
author = "Shoichiro Iwasawa and Jun Ohya and Kazuhiko Takahashi and Tatsumi Sakaguchi and Kazuyuki Ebihara and Shigeo Morishima",
year = "2000",
doi = "10.1109/AFGR.2000.840654",
language = "English",
isbn = "0769505805",
pages = "326--331",
booktitle = "Proceedings - 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Human body postures from trinocular camera images

AU - Iwasawa, Shoichiro

AU - Ohya, Jun

AU - Takahashi, Kazuhiko

AU - Sakaguchi, Tatsumi

AU - Ebihara, Kazuyuki

AU - Morishima, Shigeo

PY - 2000

Y1 - 2000

N2 - This paper proposes a new real-time method for estimating human postures in 3D from trinocular images. In this method, an upper body orientation detection and a heuristic contour analysis are performed on the human silhouettes extracted from the trinocular images so that representative points such as the top of the head can be located. The major joint positions are estimated based on a genetic algorithm-based learning procedure. 3D coordinates of the representative points and joints are then obtained from the two views by evaluating the appropriateness of the three views. The proposed method implemented on a personal computer runs in real-time. Experimental results show high estimation accuracies and the effectiveness of the view selection process.

AB - This paper proposes a new real-time method for estimating human postures in 3D from trinocular images. In this method, an upper body orientation detection and a heuristic contour analysis are performed on the human silhouettes extracted from the trinocular images so that representative points such as the top of the head can be located. The major joint positions are estimated based on a genetic algorithm-based learning procedure. 3D coordinates of the representative points and joints are then obtained from the two views by evaluating the appropriateness of the three views. The proposed method implemented on a personal computer runs in real-time. Experimental results show high estimation accuracies and the effectiveness of the view selection process.

UR - http://www.scopus.com/inward/record.url?scp=34147191379&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34147191379&partnerID=8YFLogxK

U2 - 10.1109/AFGR.2000.840654

DO - 10.1109/AFGR.2000.840654

M3 - Conference contribution

AN - SCOPUS:34147191379

SN - 0769505805

SN - 9780769505800

SP - 326

EP - 331

BT - Proceedings - 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000

PB - IEEE Computer Society

ER -