Multiple-human tracking using multiple cameras

Akira Utsumi, Hiroki Mori, Jun Ohya, Masahiko Yachida

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

34 Citations (Scopus)

Abstract

We propose a human motion detection method using multiple-viewpoint images. In vision-based human tracking, self-occlusions and human-human occlusions are a part of the more significant problems. Employing multiple viewpoints and a viewpoint selection mechanism, however, can reduce these problems. The vision system in this case should select the best viewpoints for extracting human motion information; the "best" selections can be changed among different types of target information. We address the problem of tracking human bodies. We divide the task into three primitive sub-tasks (position detection, rotation angle detection and body side detection). Each sub-task has a different criterion for selecting viewpoints and an estimation result of one sub-task can help another sub-task. We describe the criteria for accomplishing the individual sub-tasks and the relationships between sub-tasks. We have built an experimental system based on a small number of reliable image features and performed fundamental examinations on the viewpoint selection approach.

Original languageEnglish
Title of host publicationProceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998
PublisherIEEE Computer Society
Pages498-503
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

Cameras

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Utsumi, A., Mori, H., Ohya, J., & Yachida, M. (1998). Multiple-human tracking using multiple cameras. In Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998 (pp. 498-503). [670997] IEEE Computer Society. https://doi.org/10.1109/AFGR.1998.670997

Multiple-human tracking using multiple cameras. / Utsumi, Akira; Mori, Hiroki; Ohya, Jun; Yachida, Masahiko.

Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998. IEEE Computer Society, 1998. p. 498-503 670997.

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

Utsumi, A, Mori, H, Ohya, J & Yachida, M 1998, Multiple-human tracking using multiple cameras. in Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998., 670997, IEEE Computer Society, pp. 498-503, 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998, Nara, 98/4/14. https://doi.org/10.1109/AFGR.1998.670997
Utsumi A, Mori H, Ohya J, Yachida M. Multiple-human tracking using multiple cameras. In Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998. IEEE Computer Society. 1998. p. 498-503. 670997 https://doi.org/10.1109/AFGR.1998.670997
Utsumi, Akira ; Mori, Hiroki ; Ohya, Jun ; Yachida, Masahiko. / Multiple-human tracking using multiple cameras. Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998. IEEE Computer Society, 1998. pp. 498-503
@inproceedings{467abe864e644d84a3bf9f6180af4ed9,
title = "Multiple-human tracking using multiple cameras",
abstract = "We propose a human motion detection method using multiple-viewpoint images. In vision-based human tracking, self-occlusions and human-human occlusions are a part of the more significant problems. Employing multiple viewpoints and a viewpoint selection mechanism, however, can reduce these problems. The vision system in this case should select the best viewpoints for extracting human motion information; the {"}best{"} selections can be changed among different types of target information. We address the problem of tracking human bodies. We divide the task into three primitive sub-tasks (position detection, rotation angle detection and body side detection). Each sub-task has a different criterion for selecting viewpoints and an estimation result of one sub-task can help another sub-task. We describe the criteria for accomplishing the individual sub-tasks and the relationships between sub-tasks. We have built an experimental system based on a small number of reliable image features and performed fundamental examinations on the viewpoint selection approach.",
author = "Akira Utsumi and Hiroki Mori and Jun Ohya and Masahiko Yachida",
year = "1998",
doi = "10.1109/AFGR.1998.670997",
language = "English",
isbn = "0818683449",
pages = "498--503",
booktitle = "Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Multiple-human tracking using multiple cameras

AU - Utsumi, Akira

AU - Mori, Hiroki

AU - Ohya, Jun

AU - Yachida, Masahiko

PY - 1998

Y1 - 1998

N2 - We propose a human motion detection method using multiple-viewpoint images. In vision-based human tracking, self-occlusions and human-human occlusions are a part of the more significant problems. Employing multiple viewpoints and a viewpoint selection mechanism, however, can reduce these problems. The vision system in this case should select the best viewpoints for extracting human motion information; the "best" selections can be changed among different types of target information. We address the problem of tracking human bodies. We divide the task into three primitive sub-tasks (position detection, rotation angle detection and body side detection). Each sub-task has a different criterion for selecting viewpoints and an estimation result of one sub-task can help another sub-task. We describe the criteria for accomplishing the individual sub-tasks and the relationships between sub-tasks. We have built an experimental system based on a small number of reliable image features and performed fundamental examinations on the viewpoint selection approach.

AB - We propose a human motion detection method using multiple-viewpoint images. In vision-based human tracking, self-occlusions and human-human occlusions are a part of the more significant problems. Employing multiple viewpoints and a viewpoint selection mechanism, however, can reduce these problems. The vision system in this case should select the best viewpoints for extracting human motion information; the "best" selections can be changed among different types of target information. We address the problem of tracking human bodies. We divide the task into three primitive sub-tasks (position detection, rotation angle detection and body side detection). Each sub-task has a different criterion for selecting viewpoints and an estimation result of one sub-task can help another sub-task. We describe the criteria for accomplishing the individual sub-tasks and the relationships between sub-tasks. We have built an experimental system based on a small number of reliable image features and performed fundamental examinations on the viewpoint selection approach.

UR - http://www.scopus.com/inward/record.url?scp=84905400507&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905400507&partnerID=8YFLogxK

U2 - 10.1109/AFGR.1998.670997

DO - 10.1109/AFGR.1998.670997

M3 - Conference contribution

SN - 0818683449

SN - 9780818683442

SP - 498

EP - 503

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

PB - IEEE Computer Society

ER -