Full body human motion estimation on Lie groups using 3D marker position measurements

Josip Ćesić; Vladimir Joukov; Ivan Petrović; Dana Kulić

doi:10.1109/HUMANOIDS.2016.7803369

Full body human motion estimation on Lie groups using 3D marker position measurements

Josip Ćesić, Vladimir Joukov, Ivan Petrović, Dana Kulić

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

10 Citations (Scopus)

Abstract

This paper proposes a new algorithm for full body human motion estimation using 3D marker position measurements. The joints are represented with Lie group members, including special orthogonal groups SO(2) and SO(3), and a special euclidean group SE(3). We employ the Lie Group Extended Kalman Filter (LG-EKF) for stochastic inference on groups, thus explicitly accounting for the non-euclidean geometry of the state space, and provide the derivation of the LG-EKF recursion for articulated motion estimation. We evaluate the performance of the proposed algorithm in both simulation and on real-world motion capture data, comparing it with the Euler angles based EKF. The results show that the proposed filter significantly outperforms the Euler angles based EKF, since it estimates human motion more accurately and is not affected by gimbal lock.

Original language	English
Title of host publication	2016 IEEE-RAS 16th international Conference on Humanoid Robots (Humanoids 2016)
Editors	Paul Oh
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	826-833
Number of pages	8
ISBN (Electronic)	9781509047185, 9781509047178
ISBN (Print)	9781509047192
DOIs	https://doi.org/10.1109/HUMANOIDS.2016.7803369
Publication status	Published - 30 Dec 2016
Externally published	Yes
Event	IEEE-RAS International Conference on Humanoid Robots 2016 - Cancun, Mexico Duration: 15 Nov 2016 → 17 Nov 2016 Conference number: 16th

Publication series

Name	IEEE-RAS International Conference on Humanoid Robots
Publisher	IEEE, Institute of Electrical and Electronics Engineers
ISSN (Print)	2164-0572
ISSN (Electronic)	2164-0580

Conference

Conference	IEEE-RAS International Conference on Humanoid Robots 2016
Abbreviated title	Humanoids 2016
Country	Mexico
City	Cancun
Period	15/11/16 → 17/11/16

Access to Document

10.1109/HUMANOIDS.2016.7803369

Link to publication in Scopus

Cite this

Ćesić, J., Joukov, V., Petrović, I., & Kulić, D. (2016). Full body human motion estimation on Lie groups using 3D marker position measurements. In P. Oh (Ed.), 2016 IEEE-RAS 16th international Conference on Humanoid Robots (Humanoids 2016) (pp. 826-833). (IEEE-RAS International Conference on Humanoid Robots). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/HUMANOIDS.2016.7803369

Ćesić, Josip ; Joukov, Vladimir ; Petrović, Ivan ; Kulić, Dana. / Full body human motion estimation on Lie groups using 3D marker position measurements. 2016 IEEE-RAS 16th international Conference on Humanoid Robots (Humanoids 2016). editor / Paul Oh. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2016. pp. 826-833 (IEEE-RAS International Conference on Humanoid Robots).

@inproceedings{5ff925ee1e2344ee956cd7849b184cfc,

title = "Full body human motion estimation on Lie groups using 3D marker position measurements",

abstract = "This paper proposes a new algorithm for full body human motion estimation using 3D marker position measurements. The joints are represented with Lie group members, including special orthogonal groups SO(2) and SO(3), and a special euclidean group SE(3). We employ the Lie Group Extended Kalman Filter (LG-EKF) for stochastic inference on groups, thus explicitly accounting for the non-euclidean geometry of the state space, and provide the derivation of the LG-EKF recursion for articulated motion estimation. We evaluate the performance of the proposed algorithm in both simulation and on real-world motion capture data, comparing it with the Euler angles based EKF. The results show that the proposed filter significantly outperforms the Euler angles based EKF, since it estimates human motion more accurately and is not affected by gimbal lock.",

author = "Josip {\'C}esi{\'c} and Vladimir Joukov and Ivan Petrovi{\'c} and Dana Kuli{\'c}",

year = "2016",

month = dec,

day = "30",

doi = "10.1109/HUMANOIDS.2016.7803369",

language = "English",

isbn = "9781509047192",

series = "IEEE-RAS International Conference on Humanoid Robots",

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

pages = "826--833",

editor = "Paul Oh",

booktitle = "2016 IEEE-RAS 16th international Conference on Humanoid Robots (Humanoids 2016)",

address = "United States of America",

note = "IEEE-RAS International Conference on Humanoid Robots 2016, Humanoids 2016 ; Conference date: 15-11-2016 Through 17-11-2016",

}

Ćesić, J, Joukov, V, Petrović, I & Kulić, D 2016, Full body human motion estimation on Lie groups using 3D marker position measurements. in P Oh (ed.), 2016 IEEE-RAS 16th international Conference on Humanoid Robots (Humanoids 2016). IEEE-RAS International Conference on Humanoid Robots, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 826-833, IEEE-RAS International Conference on Humanoid Robots 2016, Cancun, Mexico, 15/11/16. https://doi.org/10.1109/HUMANOIDS.2016.7803369

Full body human motion estimation on Lie groups using 3D marker position measurements. / Ćesić, Josip; Joukov, Vladimir; Petrović, Ivan; Kulić, Dana.

2016 IEEE-RAS 16th international Conference on Humanoid Robots (Humanoids 2016). ed. / Paul Oh. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2016. p. 826-833 (IEEE-RAS International Conference on Humanoid Robots).

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

TY - GEN

T1 - Full body human motion estimation on Lie groups using 3D marker position measurements

AU - Ćesić, Josip

AU - Joukov, Vladimir

AU - Petrović, Ivan

AU - Kulić, Dana

N1 - Conference code: 16th

PY - 2016/12/30

Y1 - 2016/12/30

N2 - This paper proposes a new algorithm for full body human motion estimation using 3D marker position measurements. The joints are represented with Lie group members, including special orthogonal groups SO(2) and SO(3), and a special euclidean group SE(3). We employ the Lie Group Extended Kalman Filter (LG-EKF) for stochastic inference on groups, thus explicitly accounting for the non-euclidean geometry of the state space, and provide the derivation of the LG-EKF recursion for articulated motion estimation. We evaluate the performance of the proposed algorithm in both simulation and on real-world motion capture data, comparing it with the Euler angles based EKF. The results show that the proposed filter significantly outperforms the Euler angles based EKF, since it estimates human motion more accurately and is not affected by gimbal lock.

AB - This paper proposes a new algorithm for full body human motion estimation using 3D marker position measurements. The joints are represented with Lie group members, including special orthogonal groups SO(2) and SO(3), and a special euclidean group SE(3). We employ the Lie Group Extended Kalman Filter (LG-EKF) for stochastic inference on groups, thus explicitly accounting for the non-euclidean geometry of the state space, and provide the derivation of the LG-EKF recursion for articulated motion estimation. We evaluate the performance of the proposed algorithm in both simulation and on real-world motion capture data, comparing it with the Euler angles based EKF. The results show that the proposed filter significantly outperforms the Euler angles based EKF, since it estimates human motion more accurately and is not affected by gimbal lock.

UR - http://www.scopus.com/inward/record.url?scp=85010198843&partnerID=8YFLogxK

U2 - 10.1109/HUMANOIDS.2016.7803369

DO - 10.1109/HUMANOIDS.2016.7803369

M3 - Conference Paper

AN - SCOPUS:85010198843

SN - 9781509047192

T3 - IEEE-RAS International Conference on Humanoid Robots

SP - 826

EP - 833

BT - 2016 IEEE-RAS 16th international Conference on Humanoid Robots (Humanoids 2016)

A2 - Oh, Paul

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - IEEE-RAS International Conference on Humanoid Robots 2016

Y2 - 15 November 2016 through 17 November 2016

ER -

Ćesić J, Joukov V, Petrović I, Kulić D. Full body human motion estimation on Lie groups using 3D marker position measurements. In Oh P, editor, 2016 IEEE-RAS 16th international Conference on Humanoid Robots (Humanoids 2016). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2016. p. 826-833. (IEEE-RAS International Conference on Humanoid Robots). https://doi.org/10.1109/HUMANOIDS.2016.7803369