A new robust real-time method for extracting human silhouettes from color images

Masanori Yamada, Kazuyuki Ebihara, Jun Ohya

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

27 Citations (Scopus)

Abstract

A new method for extracting human silhouettes from color images in real-time regardless of changes in lighting conditions and backgrounds is proposed. In the method, RGB values of each pixel in color images acquired by a CCD camera are converted to YIQ values. Before extracting human silhouettes, the mean YIQ values of each pixel and the threshold values for the Y, I, Q components are obtained in advance from the image sequence acquired by the camera that observed the background. Based on the mean values and the threshold values, each pixel is judged whether it belongs to the human silhouette or not. The proposed method was used with the virtual metamorphosis system, in which anyone can change his or her form to any other form, and the robustness and real-time-ness were confirmed.

Original languageEnglish
Title of host publicationProceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998
PublisherIEEE Computer Society
Pages528-533
Number of pages6
ISBN (Print)0818683449, 9780818683442
DOIs
Publication statusPublished - 1998
Externally publishedYes
Event3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998 - Nara
Duration: 1998 Apr 141998 Apr 16

Other

Other3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998
CityNara
Period98/4/1498/4/16

Fingerprint

Pixels
Color
CCD cameras
Lighting
Cameras

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Yamada, M., Ebihara, K., & Ohya, J. (1998). A new robust real-time method for extracting human silhouettes from color images. In Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998 (pp. 528-533). [671002] IEEE Computer Society. https://doi.org/10.1109/AFGR.1998.671002

A new robust real-time method for extracting human silhouettes from color images. / Yamada, Masanori; Ebihara, Kazuyuki; Ohya, Jun.

Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998. IEEE Computer Society, 1998. p. 528-533 671002.

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

Yamada, M, Ebihara, K & Ohya, J 1998, A new robust real-time method for extracting human silhouettes from color images. in Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998., 671002, IEEE Computer Society, pp. 528-533, 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998, Nara, 98/4/14. https://doi.org/10.1109/AFGR.1998.671002
Yamada M, Ebihara K, Ohya J. A new robust real-time method for extracting human silhouettes from color images. In Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998. IEEE Computer Society. 1998. p. 528-533. 671002 https://doi.org/10.1109/AFGR.1998.671002
Yamada, Masanori ; Ebihara, Kazuyuki ; Ohya, Jun. / A new robust real-time method for extracting human silhouettes from color images. Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998. IEEE Computer Society, 1998. pp. 528-533
@inproceedings{ad90646b6cb84b7d982aad8d03eb417e,
title = "A new robust real-time method for extracting human silhouettes from color images",
abstract = "A new method for extracting human silhouettes from color images in real-time regardless of changes in lighting conditions and backgrounds is proposed. In the method, RGB values of each pixel in color images acquired by a CCD camera are converted to YIQ values. Before extracting human silhouettes, the mean YIQ values of each pixel and the threshold values for the Y, I, Q components are obtained in advance from the image sequence acquired by the camera that observed the background. Based on the mean values and the threshold values, each pixel is judged whether it belongs to the human silhouette or not. The proposed method was used with the virtual metamorphosis system, in which anyone can change his or her form to any other form, and the robustness and real-time-ness were confirmed.",
author = "Masanori Yamada and Kazuyuki Ebihara and Jun Ohya",
year = "1998",
doi = "10.1109/AFGR.1998.671002",
language = "English",
isbn = "0818683449",
pages = "528--533",
booktitle = "Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - A new robust real-time method for extracting human silhouettes from color images

AU - Yamada, Masanori

AU - Ebihara, Kazuyuki

AU - Ohya, Jun

PY - 1998

Y1 - 1998

N2 - A new method for extracting human silhouettes from color images in real-time regardless of changes in lighting conditions and backgrounds is proposed. In the method, RGB values of each pixel in color images acquired by a CCD camera are converted to YIQ values. Before extracting human silhouettes, the mean YIQ values of each pixel and the threshold values for the Y, I, Q components are obtained in advance from the image sequence acquired by the camera that observed the background. Based on the mean values and the threshold values, each pixel is judged whether it belongs to the human silhouette or not. The proposed method was used with the virtual metamorphosis system, in which anyone can change his or her form to any other form, and the robustness and real-time-ness were confirmed.

AB - A new method for extracting human silhouettes from color images in real-time regardless of changes in lighting conditions and backgrounds is proposed. In the method, RGB values of each pixel in color images acquired by a CCD camera are converted to YIQ values. Before extracting human silhouettes, the mean YIQ values of each pixel and the threshold values for the Y, I, Q components are obtained in advance from the image sequence acquired by the camera that observed the background. Based on the mean values and the threshold values, each pixel is judged whether it belongs to the human silhouette or not. The proposed method was used with the virtual metamorphosis system, in which anyone can change his or her form to any other form, and the robustness and real-time-ness were confirmed.

UR - http://www.scopus.com/inward/record.url?scp=84905379458&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905379458&partnerID=8YFLogxK

U2 - 10.1109/AFGR.1998.671002

DO - 10.1109/AFGR.1998.671002

M3 - Conference contribution

SN - 0818683449

SN - 9780818683442

SP - 528

EP - 533

BT - Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998

PB - IEEE Computer Society

ER -