Subspace Index Method for 3D Human Motion

Author

Xiang, Jian ; Zhu, Hongli

Author_Institution

Sch. of Inf. & Electron. Eng., ZheJiang Univ. of Sci. & Technol., Hangzhou

fYear

2007

fDate

14-17 Sept. 2007

Firstpage

67

Lastpage

69

Abstract

Along with the development of motion capture technique, more and more large-scale 3D motion databases become available. In this paper, a novel approach is presented for motion retrieval based on a novel index method. Due to high dimensionality of Motion´s features, the dimension reduction is used. Then an index system is built based on s the low-dimensional subspace tree. So we can reduce the number of costly similarity measure significantly. Experiment results show that the approaches are effective for motion data retrieval in large-scale databases.

Keywords

computer animation; content-based retrieval; motion estimation; 3D human motion; low-dimensional subspace tree; motion capture technique; motion retrieval; subspace index method; Animation; Data engineering; Educational institutions; Humans; Indexes; Information retrieval; Large-scale systems; Principal component analysis; Spatial databases; Timing;

fLanguage

English

Publisher

ieee

Conference_Titel

Bio-Inspired Computing: Theories and Applications, 2007. BIC-TA 2007. Second International Conference on

Conference_Location

Zhengzhou

Print_ISBN

978-1-4244-4105-1

Electronic_ISBN

978-1-4244-4106-8

Type

conf

DOI

10.1109/BICTA.2007.4806420

Filename

4806420