Interactive inverse kinematics for human motion  	estimation

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

doi:10.2312/PE/vriphys/vriphys09/077-084

Interactive inverse kinematics for human motion estimation

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

1 Citation (Scopus)

Abstract

We present an application of a fast interactive inverse kinematics method as a dimensionality reduction for monocular human motion estimation. The inverse kinematics solver deals efficiently and robustly with box constraints and does not suffer from shaking artifacts. The presented motion estimation system uses a single camera to estimate the motion of a human. The results show that inverse kinematics can significantly speed up the estimation process, while retaining a quality comparable to a full pose motion estimation system. Our novelty lies primarily in use of inverse kinematics to significantly speed up the particle filtering. It should be stressed that the observation part of the system has not been our focus, and as such is described only from a sense of completeness. With our approach it is possible to construct a robust and computationally efficient system for human motion estimation.

Original language	English
Title of host publication	Vriphys 09 : 6th Workshop on Virtual reality Interactions and Physical Simulations
Editors	Hartmut Prautzsch, Alfred Schmitt, Jan Bender, Matthias Teschner
Publication date	2009
Pages	77-84
ISBN (Print)	978-3-905673-73-9
DOIs	https://doi.org/10.2312/PE/vriphys/vriphys09/077-084
Publication status	Published - 2009
Event	Vriphys 2009 - Karlsruhe, Germany Duration: 5 Nov 2009 → 6 Nov 2009 Conference number: 6

Conference

Conference	Vriphys 2009
Number	6
Country/Territory	Germany
City	Karlsruhe
Period	05/11/2009 → 06/11/2009

Access to Document

10.2312/PE/vriphys/vriphys09/077-084

Cite this

Interactive inverse kinematics for human motion estimation. / Engell-Nørregård, Morten Pol; Hauberg, Søren; Lapuyade, Jerome et al.
Vriphys 09: 6th Workshop on Virtual reality Interactions and Physical Simulations. ed. / Hartmut Prautzsch; Alfred Schmitt; Jan Bender; Matthias Teschner. 2009. p. 77-84.

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

Engell-Nørregård, MP, Hauberg, S, Lapuyade, J, Erleben, K & Pedersen, KS 2009, Interactive inverse kinematics for human motion estimation. in H Prautzsch, A Schmitt, J Bender & M Teschner (eds), Vriphys 09: 6th Workshop on Virtual reality Interactions and Physical Simulations. pp. 77-84, Vriphys 2009, Karlsruhe, Germany, 05/11/2009. https://doi.org/10.2312/PE/vriphys/vriphys09/077-084

@inproceedings{de98f970ce0111dea1f3000ea68e967b,

title = "Interactive inverse kinematics for human motion estimation",

abstract = "We present an application of a fast interactive inverse kinematics method as a dimensionality reduction for monocular human motion estimation. The inverse kinematics solver deals efficiently and robustly with box constraints and does not suffer from shaking artifacts. The presented motion estimation system uses a single camera to estimate the motion of a human. The results show that inverse kinematics can significantly speed up the estimation process, while retaining a quality comparable to a full pose motion estimation system. Our novelty lies primarily in use of inverse kinematics to significantly speed up the particle filtering. It should be stressed that the observation part of the system has not been our focus, and as such is described only from a sense of completeness. With our approach it is possible to construct a robust and computationally efficient system for human motion estimation.",

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

year = "2009",

doi = "10.2312/PE/vriphys/vriphys09/077-084",

language = "English",

isbn = "978-3-905673-73-9",

pages = "77--84",

editor = "Hartmut Prautzsch and Alfred Schmitt and Jan Bender and Matthias Teschner",

booktitle = "Vriphys 09",

note = "Vriphys 2009 ; Conference date: 05-11-2009 Through 06-11-2009",

}

TY - GEN

T1 - Interactive inverse kinematics for human motion estimation

AU - Engell-Nørregård, Morten Pol

AU - Hauberg, Søren

AU - Lapuyade, Jerome

AU - Erleben, Kenny

AU - Pedersen, Kim Steenstrup

N1 - Conference code: 6

PY - 2009

Y1 - 2009

N2 - We present an application of a fast interactive inverse kinematics method as a dimensionality reduction for monocular human motion estimation. The inverse kinematics solver deals efficiently and robustly with box constraints and does not suffer from shaking artifacts. The presented motion estimation system uses a single camera to estimate the motion of a human. The results show that inverse kinematics can significantly speed up the estimation process, while retaining a quality comparable to a full pose motion estimation system. Our novelty lies primarily in use of inverse kinematics to significantly speed up the particle filtering. It should be stressed that the observation part of the system has not been our focus, and as such is described only from a sense of completeness. With our approach it is possible to construct a robust and computationally efficient system for human motion estimation.

AB - We present an application of a fast interactive inverse kinematics method as a dimensionality reduction for monocular human motion estimation. The inverse kinematics solver deals efficiently and robustly with box constraints and does not suffer from shaking artifacts. The presented motion estimation system uses a single camera to estimate the motion of a human. The results show that inverse kinematics can significantly speed up the estimation process, while retaining a quality comparable to a full pose motion estimation system. Our novelty lies primarily in use of inverse kinematics to significantly speed up the particle filtering. It should be stressed that the observation part of the system has not been our focus, and as such is described only from a sense of completeness. With our approach it is possible to construct a robust and computationally efficient system for human motion estimation.

U2 - 10.2312/PE/vriphys/vriphys09/077-084

DO - 10.2312/PE/vriphys/vriphys09/077-084

M3 - Article in proceedings

SN - 978-3-905673-73-9

SP - 77

EP - 84

BT - Vriphys 09

A2 - Prautzsch, Hartmut

A2 - Schmitt, Alfred

A2 - Bender, Jan

A2 - Teschner, Matthias

T2 - Vriphys 2009

Y2 - 5 November 2009 through 6 November 2009

ER -

Interactive inverse kinematics for human motion estimation

Abstract

Conference

Access to Document

Fingerprint

Cite this