Hierarchical visual motion retrieval system and its motion features

Seiji Okajima, Yoshihiro Okada

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

This paper proposes a hierarchical visual motion retrieval system on the web. To make it possible for the user to retrieve motion data interactively and visually on a computer screen from coarse level to fine level about motion similarity, the proposed system employs tree based visualization method for the hierarchical structure of motion data. The hierarchical structure of motion data is constructed by recursively applying k-means clustering to them. For applying k-means clustering to motion data, their similarity features should be extracted from them. In this paper, the authors also propose such motion features based on the space division quantization method and position/speed information of motions. The paper clarifies the availability of the proposed features as similarity measure among motions by quantitative evaluations using an actual motion database.

Original languageEnglish
Title of host publicationProceedings - International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, 3PGCIC 2010
Pages90-97
Number of pages8
DOIs
Publication statusPublished - Dec 1 2010
Event5th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, 3PGCIC 2010 - Fukuoka, Japan
Duration: Nov 4 2010Nov 6 2010

Other

Other5th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, 3PGCIC 2010
CountryJapan
CityFukuoka
Period11/4/1011/6/10

Fingerprint

Visualization
Availability

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Software

Cite this

Okajima, S., & Okada, Y. (2010). Hierarchical visual motion retrieval system and its motion features. In Proceedings - International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, 3PGCIC 2010 (pp. 90-97). [5664698] https://doi.org/10.1109/3PGCIC.2010.19

Hierarchical visual motion retrieval system and its motion features. / Okajima, Seiji; Okada, Yoshihiro.

Proceedings - International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, 3PGCIC 2010. 2010. p. 90-97 5664698.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Okajima, S & Okada, Y 2010, Hierarchical visual motion retrieval system and its motion features. in Proceedings - International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, 3PGCIC 2010., 5664698, pp. 90-97, 5th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, 3PGCIC 2010, Fukuoka, Japan, 11/4/10. https://doi.org/10.1109/3PGCIC.2010.19
Okajima S, Okada Y. Hierarchical visual motion retrieval system and its motion features. In Proceedings - International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, 3PGCIC 2010. 2010. p. 90-97. 5664698 https://doi.org/10.1109/3PGCIC.2010.19
Okajima, Seiji ; Okada, Yoshihiro. / Hierarchical visual motion retrieval system and its motion features. Proceedings - International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, 3PGCIC 2010. 2010. pp. 90-97
@inproceedings{01415cfb515c4e949d42e4b15f935bca,
title = "Hierarchical visual motion retrieval system and its motion features",
abstract = "This paper proposes a hierarchical visual motion retrieval system on the web. To make it possible for the user to retrieve motion data interactively and visually on a computer screen from coarse level to fine level about motion similarity, the proposed system employs tree based visualization method for the hierarchical structure of motion data. The hierarchical structure of motion data is constructed by recursively applying k-means clustering to them. For applying k-means clustering to motion data, their similarity features should be extracted from them. In this paper, the authors also propose such motion features based on the space division quantization method and position/speed information of motions. The paper clarifies the availability of the proposed features as similarity measure among motions by quantitative evaluations using an actual motion database.",
author = "Seiji Okajima and Yoshihiro Okada",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/3PGCIC.2010.19",
language = "English",
isbn = "9780769542379",
pages = "90--97",
booktitle = "Proceedings - International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, 3PGCIC 2010",

}

TY - GEN

T1 - Hierarchical visual motion retrieval system and its motion features

AU - Okajima, Seiji

AU - Okada, Yoshihiro

PY - 2010/12/1

Y1 - 2010/12/1

N2 - This paper proposes a hierarchical visual motion retrieval system on the web. To make it possible for the user to retrieve motion data interactively and visually on a computer screen from coarse level to fine level about motion similarity, the proposed system employs tree based visualization method for the hierarchical structure of motion data. The hierarchical structure of motion data is constructed by recursively applying k-means clustering to them. For applying k-means clustering to motion data, their similarity features should be extracted from them. In this paper, the authors also propose such motion features based on the space division quantization method and position/speed information of motions. The paper clarifies the availability of the proposed features as similarity measure among motions by quantitative evaluations using an actual motion database.

AB - This paper proposes a hierarchical visual motion retrieval system on the web. To make it possible for the user to retrieve motion data interactively and visually on a computer screen from coarse level to fine level about motion similarity, the proposed system employs tree based visualization method for the hierarchical structure of motion data. The hierarchical structure of motion data is constructed by recursively applying k-means clustering to them. For applying k-means clustering to motion data, their similarity features should be extracted from them. In this paper, the authors also propose such motion features based on the space division quantization method and position/speed information of motions. The paper clarifies the availability of the proposed features as similarity measure among motions by quantitative evaluations using an actual motion database.

UR - http://www.scopus.com/inward/record.url?scp=84863843025&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863843025&partnerID=8YFLogxK

U2 - 10.1109/3PGCIC.2010.19

DO - 10.1109/3PGCIC.2010.19

M3 - Conference contribution

AN - SCOPUS:84863843025

SN - 9780769542379

SP - 90

EP - 97

BT - Proceedings - International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, 3PGCIC 2010

ER -