Real-time human motion sensing based on vision-based inverse kinematics for interactive applications

Naoto Date, Hiromasa Yoshimoto, Daisaku Arita, Rin-Ichiro Taniguchi

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

13 Citations (Scopus)

Abstract

Vision-based human motion sensing has a strong merit that it does not impose any physical restrictions on humans, which provides a natural way of measuring human motion. However, its real-time processing is not easy to realize, because a human body has a high degrees of freedom, whose vision-based analysis is not simple and is usually time consuming. Here, we have developed a method in which human postures are analyzed from a limited number of visual cues. It is a combination of numerical analysis of inverse kinematics and visual search. Our method is based on a general framework of inverse kinematics, and, therefore, we can use relatively complex human figure model, which can generates natural human motion. In our experimental studies, we show that our implemented system works in real-time on a PC-cluster.

Original languageEnglish
Title of host publicationProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004
EditorsJ. Kittler, M. Petrou, M. Nixon
Pages318-321
Number of pages4
Volume3
DOIs
Publication statusPublished - Dec 20 2004
EventProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004 - Cambridge, United Kingdom
Duration: Aug 23 2004Aug 26 2004

Other

OtherProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004
CountryUnited Kingdom
CityCambridge
Period8/23/048/26/04

Fingerprint

Inverse kinematics
Numerical analysis
Processing

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Date, N., Yoshimoto, H., Arita, D., & Taniguchi, R-I. (2004). Real-time human motion sensing based on vision-based inverse kinematics for interactive applications. In J. Kittler, M. Petrou, & M. Nixon (Eds.), Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004 (Vol. 3, pp. 318-321) https://doi.org/10.1109/ICPR.2004.1334531

Real-time human motion sensing based on vision-based inverse kinematics for interactive applications. / Date, Naoto; Yoshimoto, Hiromasa; Arita, Daisaku; Taniguchi, Rin-Ichiro.

Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004. ed. / J. Kittler; M. Petrou; M. Nixon. Vol. 3 2004. p. 318-321.

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

Date, N, Yoshimoto, H, Arita, D & Taniguchi, R-I 2004, Real-time human motion sensing based on vision-based inverse kinematics for interactive applications. in J Kittler, M Petrou & M Nixon (eds), Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004. vol. 3, pp. 318-321, Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, Cambridge, United Kingdom, 8/23/04. https://doi.org/10.1109/ICPR.2004.1334531
Date N, Yoshimoto H, Arita D, Taniguchi R-I. Real-time human motion sensing based on vision-based inverse kinematics for interactive applications. In Kittler J, Petrou M, Nixon M, editors, Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004. Vol. 3. 2004. p. 318-321 https://doi.org/10.1109/ICPR.2004.1334531
Date, Naoto ; Yoshimoto, Hiromasa ; Arita, Daisaku ; Taniguchi, Rin-Ichiro. / Real-time human motion sensing based on vision-based inverse kinematics for interactive applications. Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004. editor / J. Kittler ; M. Petrou ; M. Nixon. Vol. 3 2004. pp. 318-321
@inproceedings{a714ea4f86d84bf2bfc23e4d30f67886,
title = "Real-time human motion sensing based on vision-based inverse kinematics for interactive applications",
abstract = "Vision-based human motion sensing has a strong merit that it does not impose any physical restrictions on humans, which provides a natural way of measuring human motion. However, its real-time processing is not easy to realize, because a human body has a high degrees of freedom, whose vision-based analysis is not simple and is usually time consuming. Here, we have developed a method in which human postures are analyzed from a limited number of visual cues. It is a combination of numerical analysis of inverse kinematics and visual search. Our method is based on a general framework of inverse kinematics, and, therefore, we can use relatively complex human figure model, which can generates natural human motion. In our experimental studies, we show that our implemented system works in real-time on a PC-cluster.",
author = "Naoto Date and Hiromasa Yoshimoto and Daisaku Arita and Rin-Ichiro Taniguchi",
year = "2004",
month = "12",
day = "20",
doi = "10.1109/ICPR.2004.1334531",
language = "English",
isbn = "0769521282",
volume = "3",
pages = "318--321",
editor = "J. Kittler and M. Petrou and M. Nixon",
booktitle = "Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004",

}

TY - GEN

T1 - Real-time human motion sensing based on vision-based inverse kinematics for interactive applications

AU - Date, Naoto

AU - Yoshimoto, Hiromasa

AU - Arita, Daisaku

AU - Taniguchi, Rin-Ichiro

PY - 2004/12/20

Y1 - 2004/12/20

N2 - Vision-based human motion sensing has a strong merit that it does not impose any physical restrictions on humans, which provides a natural way of measuring human motion. However, its real-time processing is not easy to realize, because a human body has a high degrees of freedom, whose vision-based analysis is not simple and is usually time consuming. Here, we have developed a method in which human postures are analyzed from a limited number of visual cues. It is a combination of numerical analysis of inverse kinematics and visual search. Our method is based on a general framework of inverse kinematics, and, therefore, we can use relatively complex human figure model, which can generates natural human motion. In our experimental studies, we show that our implemented system works in real-time on a PC-cluster.

AB - Vision-based human motion sensing has a strong merit that it does not impose any physical restrictions on humans, which provides a natural way of measuring human motion. However, its real-time processing is not easy to realize, because a human body has a high degrees of freedom, whose vision-based analysis is not simple and is usually time consuming. Here, we have developed a method in which human postures are analyzed from a limited number of visual cues. It is a combination of numerical analysis of inverse kinematics and visual search. Our method is based on a general framework of inverse kinematics, and, therefore, we can use relatively complex human figure model, which can generates natural human motion. In our experimental studies, we show that our implemented system works in real-time on a PC-cluster.

UR - http://www.scopus.com/inward/record.url?scp=10044275031&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10044275031&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2004.1334531

DO - 10.1109/ICPR.2004.1334531

M3 - Conference contribution

SN - 0769521282

VL - 3

SP - 318

EP - 321

BT - Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004

A2 - Kittler, J.

A2 - Petrou, M.

A2 - Nixon, M.

ER -