Tensor analysis and multi-scale features based multi-view human action recognition

Author

Jia, Chengcheng ; Wang, Sujing ; Xu, Xiangli ; Zhou, Chunguang ; Zhang, Libiao

Author_Institution

Coll. of Comput. Sci. & Technol., Jilin Univ., Changchun, China

Volume

4

fYear

2010

fDate

16-18 April 2010

Abstract

A method of multi-view human action recognition based on multi-scale features via tensor analysis is proposed. A series of silhouettes are transformed to a Serials-Frame image, from which the multi-scale features are extracted to construct the eigenSpace of a tensor, which named Serials-Frame Tensor (SF-Tensor). The SF-Tensor subspace analysis is applied to separate the variable views and people information to recognize different actions. Experiment results obtained show that the proposed method attains a good recognition rate and improves the efficiency significantly.

Keywords

eigenvalues and eigenfunctions; feature extraction; image motion analysis; tensors; eigenspace; multiscale features; multiview human action recognition; serials frame image; serials frame tensor; silhouettes; tensor analysis; Application software; Educational institutions; Face recognition; Feature extraction; Handicapped aids; Hidden Markov models; Humans; Image reconstruction; Motion analysis; Tensile stress; SF-tensor; action recognition; multi-scale features; multi-view;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Engineering and Technology (ICCET), 2010 2nd International Conference on

Conference_Location

Chengdu

Print_ISBN

978-1-4244-6347-3

Type

conf

DOI

10.1109/ICCET.2010.5485732

Filename

5485732