Human motion capture data recovery via trajectory-based sparse representation

Junhui Hou; Lap Pui Chau; Ying He; Jie Chen; Nadia Magnenat-Thalmann

doi:10.1109/ICIP.2013.6738146

Human motion capture data recovery via trajectory-based sparse representation

Junhui Hou
, Lap Pui Chau
, Ying He
, Jie Chen
, Nadia Magnenat-Thalmann

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

23 Citations (Scopus)

Abstract

Motion capture is widely used in sports, entertainment and medical applications. An important issue is to recover motion capture data that has been corrupted by noise and missing data entries during acquisition. In this paper, we propose a new method to recover corrupted motion capture data through trajectory-based sparse representation. The data is firstly represented as trajectories with fixed length and high correlation. Then, based on the sparse representation theory, the original trajectories can be recovered by solving the sparse representation of the incomplete trajectories through the OMP algorithm using a dictionary learned by K-SVD. Experimental results show that the proposed algorithm achieves much better performance, especially when significant portions of data is missing, than the existing algorithms.

Original language	English
Title of host publication	2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
Publisher	IEEE
Pages	709-713
Number of pages	5
ISBN (Print)	9781479923410
DOIs	https://doi.org/10.1109/ICIP.2013.6738146
Publication status	Published - 15 Sept 2013
Event	2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC, Australia Duration: 15 Sept 2013 → 18 Sept 2013 https://doi.org/10.1109/ICIP15918.2013 (Conference proceeding)

Publication series

Name	IEEE International Conference on Image Processing, ICIP - Proceedings

Conference

Conference	2013 20th IEEE International Conference on Image Processing, ICIP 2013
Abbreviated title	ICIP 2013
Country/Territory	Australia
City	Melbourne, VIC
Period	15/09/13 → 18/09/13
Internet address	https://doi.org/10.1109/ICIP15918.2013 (Conference proceeding)

User-Defined Keywords

completing
K-SVD
Motion capture
sparse representation
trajectory

Access to Document

10.1109/ICIP.2013.6738146

Cite this

@inproceedings{8fd40f11f5e54a30b3ec8006c0dd538f,

title = "Human motion capture data recovery via trajectory-based sparse representation",

abstract = "Motion capture is widely used in sports, entertainment and medical applications. An important issue is to recover motion capture data that has been corrupted by noise and missing data entries during acquisition. In this paper, we propose a new method to recover corrupted motion capture data through trajectory-based sparse representation. The data is firstly represented as trajectories with fixed length and high correlation. Then, based on the sparse representation theory, the original trajectories can be recovered by solving the sparse representation of the incomplete trajectories through the OMP algorithm using a dictionary learned by K-SVD. Experimental results show that the proposed algorithm achieves much better performance, especially when significant portions of data is missing, than the existing algorithms.",

keywords = "completing, K-SVD, Motion capture, sparse representation, trajectory",

author = "Junhui Hou and Chau, \{Lap Pui\} and Ying He and Jie Chen and Nadia Magnenat-Thalmann",

note = "Publisher Copyright: {\textcopyright} 2013, IEEE.; 2013 20th IEEE International Conference on Image Processing, ICIP 2013, ICIP 2013 ; Conference date: 15-09-2013 Through 18-09-2013",

year = "2013",

month = sep,

day = "15",

doi = "10.1109/ICIP.2013.6738146",

language = "English",

isbn = "9781479923410",

series = "IEEE International Conference on Image Processing, ICIP - Proceedings",

publisher = "IEEE",

pages = "709--713",

booktitle = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",

address = "United States",

url = "https://doi.org/10.1109/ICIP15918.2013",

}

Hou, J, Chau, LP, He, Y, Chen, J & Magnenat-Thalmann, N 2013, Human motion capture data recovery via trajectory-based sparse representation. in 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. IEEE International Conference on Image Processing, ICIP - Proceedings, IEEE, pp. 709-713, 2013 20th IEEE International Conference on Image Processing, ICIP 2013, Melbourne, VIC, Australia, 15/09/13. https://doi.org/10.1109/ICIP.2013.6738146

Human motion capture data recovery via trajectory-based sparse representation. / Hou, Junhui; Chau, Lap Pui; He, Ying et al.
2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. IEEE, 2013. p. 709-713 (IEEE International Conference on Image Processing, ICIP - Proceedings).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Human motion capture data recovery via trajectory-based sparse representation

AU - Hou, Junhui

AU - Chau, Lap Pui

AU - He, Ying

AU - Chen, Jie

AU - Magnenat-Thalmann, Nadia

PY - 2013/9/15

Y1 - 2013/9/15

N2 - Motion capture is widely used in sports, entertainment and medical applications. An important issue is to recover motion capture data that has been corrupted by noise and missing data entries during acquisition. In this paper, we propose a new method to recover corrupted motion capture data through trajectory-based sparse representation. The data is firstly represented as trajectories with fixed length and high correlation. Then, based on the sparse representation theory, the original trajectories can be recovered by solving the sparse representation of the incomplete trajectories through the OMP algorithm using a dictionary learned by K-SVD. Experimental results show that the proposed algorithm achieves much better performance, especially when significant portions of data is missing, than the existing algorithms.

AB - Motion capture is widely used in sports, entertainment and medical applications. An important issue is to recover motion capture data that has been corrupted by noise and missing data entries during acquisition. In this paper, we propose a new method to recover corrupted motion capture data through trajectory-based sparse representation. The data is firstly represented as trajectories with fixed length and high correlation. Then, based on the sparse representation theory, the original trajectories can be recovered by solving the sparse representation of the incomplete trajectories through the OMP algorithm using a dictionary learned by K-SVD. Experimental results show that the proposed algorithm achieves much better performance, especially when significant portions of data is missing, than the existing algorithms.

KW - completing

KW - K-SVD

KW - Motion capture

KW - sparse representation

KW - trajectory

UR - https://www.scopus.com/pages/publications/84897785281

U2 - 10.1109/ICIP.2013.6738146

DO - 10.1109/ICIP.2013.6738146

M3 - Conference proceeding

AN - SCOPUS:84897785281

SN - 9781479923410

T3 - IEEE International Conference on Image Processing, ICIP - Proceedings

SP - 709

EP - 713

BT - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

PB - IEEE

T2 - 2013 20th IEEE International Conference on Image Processing, ICIP 2013

Y2 - 15 September 2013 through 18 September 2013

ER -

Human motion capture data recovery via trajectory-based sparse representation

Abstract

Publication series

Conference

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this