Three dimensional monocular human motion analysis in end-effector space

Søren Hauberg; Jerome Lapuyade; Morten Pol Engell-Nørregård; Kenny Erleben; Kim Steenstrup Pedersen

doi:10.1007/978-3-642-03641-5_18

Three dimensional monocular human motion analysis in end-effector space

Søren Hauberg, Jerome Lapuyade, Morten Pol Engell-Nørregård, Kenny Erleben, Kim Steenstrup Pedersen

Department of Computer Science

7 Citations (Scopus)

49 Downloads (Pure)

Abstract

In this paper, we present a novel approach to three dimensional human motion estimation from monocular video data. We employ a particle filter to perform the motion estimation. The novelty of the method lies in the choice of state space for the particle filter. Using a non-linear inverse kinematics solver allows us to perform the filtering in end-effector space. This effectively reduces the dimensionality of the state space while still allowing for the estimation of a large set of motions. Preliminary experiments with the strategy show good results compared to a full-pose tracker.

Original language	English
Title of host publication	Energy Minimization Methods in Computer Vision and Pattern Recognition : 7th International Conference, EMMCVPR 2009, Bonn, Germany, August 24-27, 2009. Proceedings
Editors	Daniel Cremers, Yuri Boykov, Andrew Blake, Frank R. Schmidt
Number of pages	14
Publisher	Springer
Publication date	2009
Pages	235-248
ISBN (Print)	978-3-642-03640-8
ISBN (Electronic)	978-3-642-03641-5
DOIs	https://doi.org/10.1007/978-3-642-03641-5_18
Publication status	Published - 2009
Event	7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition - Bonn, Germany Duration: 24 Aug 2009 → 27 Aug 2009 Conference number: 7

Conference

Conference	7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Number	7
Country/Territory	Germany
City	Bonn
Period	24/08/2009 → 27/08/2009

Series	Lecture notes in computer science
Volume	5681
ISSN	0302-9743

Keywords

Faculty of Science

Access to Document

10.1007/978-3-642-03641-5_18

Emmcvpr2009Accepted author manuscript, 2.03 MB

Cite this

Hauberg, S., Lapuyade, J., Engell-Nørregård, M. P., Erleben, K., & Pedersen, K. S. (2009). Three dimensional monocular human motion analysis in end-effector space. In D. Cremers, Y. Boykov, A. Blake, & F. R. Schmidt (Eds.), Energy Minimization Methods in Computer Vision and Pattern Recognition: 7th International Conference, EMMCVPR 2009, Bonn, Germany, August 24-27, 2009. Proceedings (pp. 235-248). Springer. https://doi.org/10.1007/978-3-642-03641-5_18

Three dimensional monocular human motion analysis in end-effector space. / Hauberg, Søren; Lapuyade, Jerome; Engell-Nørregård, Morten Pol et al.
Energy Minimization Methods in Computer Vision and Pattern Recognition: 7th International Conference, EMMCVPR 2009, Bonn, Germany, August 24-27, 2009. Proceedings. ed. / Daniel Cremers; Yuri Boykov; Andrew Blake; Frank R. Schmidt. Springer, 2009. p. 235-248 (Lecture notes in computer science, Vol. 5681).

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

Hauberg, S, Lapuyade, J, Engell-Nørregård, MP, Erleben, K & Pedersen, KS 2009, Three dimensional monocular human motion analysis in end-effector space. in D Cremers, Y Boykov, A Blake & FR Schmidt (eds), Energy Minimization Methods in Computer Vision and Pattern Recognition: 7th International Conference, EMMCVPR 2009, Bonn, Germany, August 24-27, 2009. Proceedings. Springer, Lecture notes in computer science, vol. 5681, pp. 235-248, 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition, Bonn, Germany, 24/08/2009. https://doi.org/10.1007/978-3-642-03641-5_18

Hauberg S, Lapuyade J, Engell-Nørregård MP, Erleben K , Pedersen KS. Three dimensional monocular human motion analysis in end-effector space. In Cremers D, Boykov Y, Blake A, Schmidt FR, editors, Energy Minimization Methods in Computer Vision and Pattern Recognition: 7th International Conference, EMMCVPR 2009, Bonn, Germany, August 24-27, 2009. Proceedings. Springer. 2009. p. 235-248. (Lecture notes in computer science, Vol. 5681). doi: 10.1007/978-3-642-03641-5_18

Hauberg, Søren ; Lapuyade, Jerome ; Engell-Nørregård, Morten Pol et al. / Three dimensional monocular human motion analysis in end-effector space. Energy Minimization Methods in Computer Vision and Pattern Recognition: 7th International Conference, EMMCVPR 2009, Bonn, Germany, August 24-27, 2009. Proceedings. editor / Daniel Cremers ; Yuri Boykov ; Andrew Blake ; Frank R. Schmidt. Springer, 2009. pp. 235-248 (Lecture notes in computer science, Vol. 5681).

@inproceedings{85518be0a29e11debc73000ea68e967b,

title = "Three dimensional monocular human motion analysis in end-effector space",

abstract = "In this paper, we present a novel approach to three dimensional human motion estimation from monocular video data. We employ a particle filter to perform the motion estimation. The novelty of the method lies in the choice of state space for the particle filter. Using a non-linear inverse kinematics solver allows us to perform the filtering in end-effector space. This effectively reduces the dimensionality of the state space while still allowing for the estimation of a large set of motions. Preliminary experiments with the strategy show good results compared to a full-pose tracker.",

keywords = "Faculty of Science",

author = "S{\o}ren Hauberg and Jerome Lapuyade and Engell-N{\o}rreg{\aa}rd, {Morten Pol} and Kenny Erleben and Pedersen, {Kim Steenstrup}",

year = "2009",

doi = "10.1007/978-3-642-03641-5_18",

language = "English",

isbn = "978-3-642-03640-8",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "235--248",

editor = "Daniel Cremers and Yuri Boykov and Andrew Blake and Schmidt, {Frank R.}",

booktitle = "Energy Minimization Methods in Computer Vision and Pattern Recognition",

note = "7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition ; Conference date: 24-08-2009 Through 27-08-2009",

}

TY - GEN

T1 - Three dimensional monocular human motion analysis in end-effector space

AU - Hauberg, Søren

AU - Lapuyade, Jerome

AU - Engell-Nørregård, Morten Pol

AU - Erleben, Kenny

AU - Pedersen, Kim Steenstrup

N1 - Conference code: 7

PY - 2009

Y1 - 2009

N2 - In this paper, we present a novel approach to three dimensional human motion estimation from monocular video data. We employ a particle filter to perform the motion estimation. The novelty of the method lies in the choice of state space for the particle filter. Using a non-linear inverse kinematics solver allows us to perform the filtering in end-effector space. This effectively reduces the dimensionality of the state space while still allowing for the estimation of a large set of motions. Preliminary experiments with the strategy show good results compared to a full-pose tracker.

AB - In this paper, we present a novel approach to three dimensional human motion estimation from monocular video data. We employ a particle filter to perform the motion estimation. The novelty of the method lies in the choice of state space for the particle filter. Using a non-linear inverse kinematics solver allows us to perform the filtering in end-effector space. This effectively reduces the dimensionality of the state space while still allowing for the estimation of a large set of motions. Preliminary experiments with the strategy show good results compared to a full-pose tracker.

KW - Faculty of Science

U2 - 10.1007/978-3-642-03641-5_18

DO - 10.1007/978-3-642-03641-5_18

M3 - Article in proceedings

SN - 978-3-642-03640-8

T3 - Lecture notes in computer science

SP - 235

EP - 248

BT - Energy Minimization Methods in Computer Vision and Pattern Recognition

A2 - Cremers, Daniel

A2 - Boykov, Yuri

A2 - Blake, Andrew

A2 - Schmidt, Frank R.

PB - Springer

T2 - 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition

Y2 - 24 August 2009 through 27 August 2009

ER -

Three dimensional monocular human motion analysis in end-effector space

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this