Data-driven online motion analysis

Tianyu Huang; Jia Yang; Jie Li

doi:10.1109/CAIDCD.2009.5374981

Data-driven online motion analysis

Tianyu Huang^*, Jia Yang, Jie Li

^*Corresponding author for this work

School of Computer Science and Technology

Beijing Institute of Technology

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

1 Citation (Scopus)

Abstract

The paper proposed an online analysis for motion captured motion data. Traditional manifold-based motion analysis can only perform in offline mode, which limits the applications and developments of the data-driven computer animation. By reserving the eigenspace and reconstructing the space using only the new instance, online motion analysis can be achieved. Numerical new training instances can be extended while maintaining the reasonable dimensions. The experiments results demonstrated the feasibility and merits.

Original language	English
Title of host publication	Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design
Subtitle of host publication	E-Business, Creative Design, Manufacturing - CAID and CD'2009
Pages	1407-1411
Number of pages	5
DOIs	https://doi.org/10.1109/CAIDCD.2009.5374981
Publication status	Published - 2009
Event	2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009 - Wenzhou, China Duration: 26 Nov 2009 → 29 Nov 2009

Publication series

Name	Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009

Conference

Conference	2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009
Country/Territory	China
City	Wenzhou
Period	26/11/09 → 29/11/09

Keywords

Captured motion data
Eigenspace reconstruction
Incremental online PCA
Online motion analysis
Principal component analysis

Access to Document

10.1109/CAIDCD.2009.5374981

Cite this

Huang, T., Yang, J., & Li, J. (2009). Data-driven online motion analysis. In Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009 (pp. 1407-1411). Article 5374981 (Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009). https://doi.org/10.1109/CAIDCD.2009.5374981

Huang, Tianyu ; Yang, Jia ; Li, Jie. / Data-driven online motion analysis. Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009. 2009. pp. 1407-1411 (Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009).

@inproceedings{08ab62b8127b431dabe4c63dadc072d5,

title = "Data-driven online motion analysis",

abstract = "The paper proposed an online analysis for motion captured motion data. Traditional manifold-based motion analysis can only perform in offline mode, which limits the applications and developments of the data-driven computer animation. By reserving the eigenspace and reconstructing the space using only the new instance, online motion analysis can be achieved. Numerical new training instances can be extended while maintaining the reasonable dimensions. The experiments results demonstrated the feasibility and merits.",

keywords = "Captured motion data, Eigenspace reconstruction, Incremental online PCA, Online motion analysis, Principal component analysis",

author = "Tianyu Huang and Jia Yang and Jie Li",

year = "2009",

doi = "10.1109/CAIDCD.2009.5374981",

language = "English",

isbn = "9781424452675",

series = "Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009",

pages = "1407--1411",

booktitle = "Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design",

note = "2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009 ; Conference date: 26-11-2009 Through 29-11-2009",

}

Huang, T, Yang, J & Li, J 2009, Data-driven online motion analysis. in Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009., 5374981, Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009, pp. 1407-1411, 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009, Wenzhou, China, 26/11/09. https://doi.org/10.1109/CAIDCD.2009.5374981

Data-driven online motion analysis. / Huang, Tianyu; Yang, Jia; Li, Jie.
Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009. 2009. p. 1407-1411 5374981 (Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009).

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

TY - GEN

T1 - Data-driven online motion analysis

AU - Huang, Tianyu

AU - Yang, Jia

AU - Li, Jie

PY - 2009

Y1 - 2009

N2 - The paper proposed an online analysis for motion captured motion data. Traditional manifold-based motion analysis can only perform in offline mode, which limits the applications and developments of the data-driven computer animation. By reserving the eigenspace and reconstructing the space using only the new instance, online motion analysis can be achieved. Numerical new training instances can be extended while maintaining the reasonable dimensions. The experiments results demonstrated the feasibility and merits.

AB - The paper proposed an online analysis for motion captured motion data. Traditional manifold-based motion analysis can only perform in offline mode, which limits the applications and developments of the data-driven computer animation. By reserving the eigenspace and reconstructing the space using only the new instance, online motion analysis can be achieved. Numerical new training instances can be extended while maintaining the reasonable dimensions. The experiments results demonstrated the feasibility and merits.

KW - Captured motion data

KW - Eigenspace reconstruction

KW - Incremental online PCA

KW - Online motion analysis

KW - Principal component analysis

UR - http://www.scopus.com/inward/record.url?scp=77949579747&partnerID=8YFLogxK

U2 - 10.1109/CAIDCD.2009.5374981

DO - 10.1109/CAIDCD.2009.5374981

M3 - Conference contribution

AN - SCOPUS:77949579747

SN - 9781424452675

T3 - Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009

SP - 1407

EP - 1411

BT - Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design

T2 - 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009

Y2 - 26 November 2009 through 29 November 2009

ER -

Huang T, Yang J, Li J. Data-driven online motion analysis. In Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009. 2009. p. 1407-1411. 5374981. (Proceeding 2009 IEEE 10th International Conference on Computer-Aided Industrial Design and Conceptual Design: E-Business, Creative Design, Manufacturing - CAID and CD'2009). doi: 10.1109/CAIDCD.2009.5374981

Data-driven online motion analysis

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this