Particle filter based human motion tracking

Zhenning Li; Dana Kulić

doi:10.1109/ICARCV.2010.5707796

Particle filter based human motion tracking

Zhenning Li, Dana Kulić

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

5 Citations (Scopus)

Abstract

This paper proposes a particle filter based markerless upper body motion capture system, capable of running in realtime. This system is designed for a humanoid robot application, and thus a monocular image sequence is used as input. We first set up a model of the human body, a sub-model which includes 11 Degrees of Freedom is used for the upper body tracking. Considering the realtime processing requirements, two time efficient cues are implemented in the likelihood calculation, namely the edge cue and the distance cue. The system is tested using a publicly available database, which consists of both the videos and the ground truth data, enabling quantitative error analysis. The system successfully tracks the human through arbitrary upper body motion at 20Hz.

Original language	English
Title of host publication	11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	555-560
Number of pages	6
ISBN (Print)	9781424478132
DOIs	https://doi.org/10.1109/ICARCV.2010.5707796
Publication status	Published - 1 Dec 2010
Externally published	Yes
Event	International Conference on Control, Automation, Robotics and Vision 2010 - Singapore, Singapore Duration: 7 Dec 2010 → 10 Dec 2010 Conference number: 11th https://ieeexplore.ieee.org/xpl/conhome/5702939/proceeding (Proceedings)

Publication series

Name	11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010

Conference

Conference	International Conference on Control, Automation, Robotics and Vision 2010
Abbreviated title	ICARV 2010
Country/Territory	Singapore
City	Singapore
Period	7/12/10 → 10/12/10
Internet address	https://ieeexplore.ieee.org/xpl/conhome/5702939/proceeding (Proceedings)

Keywords

Human motion capture
Marker-less
Particle filter
Quantitative error analysis
Realtime

Access to Document

10.1109/ICARCV.2010.5707796

Cite this

@inproceedings{d25476fdb3f349eaa6a1f7490624251e,

title = "Particle filter based human motion tracking",

abstract = "This paper proposes a particle filter based markerless upper body motion capture system, capable of running in realtime. This system is designed for a humanoid robot application, and thus a monocular image sequence is used as input. We first set up a model of the human body, a sub-model which includes 11 Degrees of Freedom is used for the upper body tracking. Considering the realtime processing requirements, two time efficient cues are implemented in the likelihood calculation, namely the edge cue and the distance cue. The system is tested using a publicly available database, which consists of both the videos and the ground truth data, enabling quantitative error analysis. The system successfully tracks the human through arbitrary upper body motion at 20Hz.",

keywords = "Human motion capture, Marker-less, Particle filter, Quantitative error analysis, Realtime",

author = "Zhenning Li and Dana Kuli{\'c}",

year = "2010",

month = dec,

day = "1",

doi = "10.1109/ICARCV.2010.5707796",

language = "English",

isbn = "9781424478132",

series = "11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

pages = "555--560",

booktitle = "11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010",

address = "United States of America",

note = "International Conference on Control, Automation, Robotics and Vision 2010, ICARV 2010 ; Conference date: 07-12-2010 Through 10-12-2010",

url = "https://ieeexplore.ieee.org/xpl/conhome/5702939/proceeding",

}

Li, Z & Kulić, D 2010, Particle filter based human motion tracking. in 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010. 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010, IEEE, Institute of Electrical and Electronics Engineers, pp. 555-560, International Conference on Control, Automation, Robotics and Vision 2010, Singapore, Singapore, 7/12/10. https://doi.org/10.1109/ICARCV.2010.5707796

Particle filter based human motion tracking. / Li, Zhenning; Kulić, Dana.
11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010. IEEE, Institute of Electrical and Electronics Engineers, 2010. p. 555-560 (11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Particle filter based human motion tracking

AU - Li, Zhenning

AU - Kulić, Dana

N1 - Conference code: 11th

PY - 2010/12/1

Y1 - 2010/12/1

N2 - This paper proposes a particle filter based markerless upper body motion capture system, capable of running in realtime. This system is designed for a humanoid robot application, and thus a monocular image sequence is used as input. We first set up a model of the human body, a sub-model which includes 11 Degrees of Freedom is used for the upper body tracking. Considering the realtime processing requirements, two time efficient cues are implemented in the likelihood calculation, namely the edge cue and the distance cue. The system is tested using a publicly available database, which consists of both the videos and the ground truth data, enabling quantitative error analysis. The system successfully tracks the human through arbitrary upper body motion at 20Hz.

AB - This paper proposes a particle filter based markerless upper body motion capture system, capable of running in realtime. This system is designed for a humanoid robot application, and thus a monocular image sequence is used as input. We first set up a model of the human body, a sub-model which includes 11 Degrees of Freedom is used for the upper body tracking. Considering the realtime processing requirements, two time efficient cues are implemented in the likelihood calculation, namely the edge cue and the distance cue. The system is tested using a publicly available database, which consists of both the videos and the ground truth data, enabling quantitative error analysis. The system successfully tracks the human through arbitrary upper body motion at 20Hz.

KW - Human motion capture

KW - Marker-less

KW - Particle filter

KW - Quantitative error analysis

KW - Realtime

UR - https://www.scopus.com/pages/publications/79952431965

U2 - 10.1109/ICARCV.2010.5707796

DO - 10.1109/ICARCV.2010.5707796

M3 - Conference Paper

AN - SCOPUS:79952431965

SN - 9781424478132

T3 - 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010

SP - 555

EP - 560

BT - 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - International Conference on Control, Automation, Robotics and Vision 2010

Y2 - 7 December 2010 through 10 December 2010

ER -

Particle filter based human motion tracking

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this