Real-time tracking of multiple people using unlabelled markers and its application in interactive dance

Daniel Whiteley, Gang Qian, Thanassis Rikakis, Jodi James, Todd Ingalls, Siew Wang, Loren Olson

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

This paper describes an approach to tracking the global locations of multiple dancers using marker-based motion capture system from only unlabeled 3D marker data for the application of interactive dance. This algorithm is based on the fact that in the presence of multiple people, marker labeling is poor or even infeasible, while reconstruction of the marker 3D coordinates is still reasonable. The tracking of dancers is done through treating dancers with markers as point clouds that have noticeable characteristics. Such characteristics include fixed marker set, all the markers being within an average wingspan, and that the markers on a dancer are closely bounded together. Using these characteristics, a blurring process was used to find the location of the dancers, and a mean shift algorithm was implemented to track them. Satisfactory results have been obtained using the proposed method.

Original languageEnglish (US)
DOIs
StatePublished - Jan 1 2005
Event2005 16th British Machine Vision Conference, BMVC 2005 - Oxford, United Kingdom
Duration: Sep 5 2005Sep 8 2005

Conference

Conference2005 16th British Machine Vision Conference, BMVC 2005
CountryUnited Kingdom
CityOxford
Period9/5/059/8/05

Fingerprint

Labeling

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Whiteley, D., Qian, G., Rikakis, T., James, J., Ingalls, T., Wang, S., & Olson, L. (2005). Real-time tracking of multiple people using unlabelled markers and its application in interactive dance. Paper presented at 2005 16th British Machine Vision Conference, BMVC 2005, Oxford, United Kingdom. https://doi.org/10.5244/C.19.74

Real-time tracking of multiple people using unlabelled markers and its application in interactive dance. / Whiteley, Daniel; Qian, Gang; Rikakis, Thanassis; James, Jodi; Ingalls, Todd; Wang, Siew; Olson, Loren.

2005. Paper presented at 2005 16th British Machine Vision Conference, BMVC 2005, Oxford, United Kingdom.

Research output: Contribution to conferencePaper

Whiteley, D, Qian, G, Rikakis, T, James, J, Ingalls, T, Wang, S & Olson, L 2005, 'Real-time tracking of multiple people using unlabelled markers and its application in interactive dance' Paper presented at 2005 16th British Machine Vision Conference, BMVC 2005, Oxford, United Kingdom, 9/5/05 - 9/8/05, . https://doi.org/10.5244/C.19.74
Whiteley D, Qian G, Rikakis T, James J, Ingalls T, Wang S et al. Real-time tracking of multiple people using unlabelled markers and its application in interactive dance. 2005. Paper presented at 2005 16th British Machine Vision Conference, BMVC 2005, Oxford, United Kingdom. https://doi.org/10.5244/C.19.74
Whiteley, Daniel ; Qian, Gang ; Rikakis, Thanassis ; James, Jodi ; Ingalls, Todd ; Wang, Siew ; Olson, Loren. / Real-time tracking of multiple people using unlabelled markers and its application in interactive dance. Paper presented at 2005 16th British Machine Vision Conference, BMVC 2005, Oxford, United Kingdom.
@conference{9224bd0388b04764a3e7f9b2133507f1,
title = "Real-time tracking of multiple people using unlabelled markers and its application in interactive dance",
abstract = "This paper describes an approach to tracking the global locations of multiple dancers using marker-based motion capture system from only unlabeled 3D marker data for the application of interactive dance. This algorithm is based on the fact that in the presence of multiple people, marker labeling is poor or even infeasible, while reconstruction of the marker 3D coordinates is still reasonable. The tracking of dancers is done through treating dancers with markers as point clouds that have noticeable characteristics. Such characteristics include fixed marker set, all the markers being within an average wingspan, and that the markers on a dancer are closely bounded together. Using these characteristics, a blurring process was used to find the location of the dancers, and a mean shift algorithm was implemented to track them. Satisfactory results have been obtained using the proposed method.",
author = "Daniel Whiteley and Gang Qian and Thanassis Rikakis and Jodi James and Todd Ingalls and Siew Wang and Loren Olson",
year = "2005",
month = "1",
day = "1",
doi = "10.5244/C.19.74",
language = "English (US)",
note = "2005 16th British Machine Vision Conference, BMVC 2005 ; Conference date: 05-09-2005 Through 08-09-2005",

}

TY - CONF

T1 - Real-time tracking of multiple people using unlabelled markers and its application in interactive dance

AU - Whiteley, Daniel

AU - Qian, Gang

AU - Rikakis, Thanassis

AU - James, Jodi

AU - Ingalls, Todd

AU - Wang, Siew

AU - Olson, Loren

PY - 2005/1/1

Y1 - 2005/1/1

N2 - This paper describes an approach to tracking the global locations of multiple dancers using marker-based motion capture system from only unlabeled 3D marker data for the application of interactive dance. This algorithm is based on the fact that in the presence of multiple people, marker labeling is poor or even infeasible, while reconstruction of the marker 3D coordinates is still reasonable. The tracking of dancers is done through treating dancers with markers as point clouds that have noticeable characteristics. Such characteristics include fixed marker set, all the markers being within an average wingspan, and that the markers on a dancer are closely bounded together. Using these characteristics, a blurring process was used to find the location of the dancers, and a mean shift algorithm was implemented to track them. Satisfactory results have been obtained using the proposed method.

AB - This paper describes an approach to tracking the global locations of multiple dancers using marker-based motion capture system from only unlabeled 3D marker data for the application of interactive dance. This algorithm is based on the fact that in the presence of multiple people, marker labeling is poor or even infeasible, while reconstruction of the marker 3D coordinates is still reasonable. The tracking of dancers is done through treating dancers with markers as point clouds that have noticeable characteristics. Such characteristics include fixed marker set, all the markers being within an average wingspan, and that the markers on a dancer are closely bounded together. Using these characteristics, a blurring process was used to find the location of the dancers, and a mean shift algorithm was implemented to track them. Satisfactory results have been obtained using the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=84898404397&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898404397&partnerID=8YFLogxK

U2 - 10.5244/C.19.74

DO - 10.5244/C.19.74

M3 - Paper

AN - SCOPUS:84898404397

ER -