Action Recognition by Fusing Spatial-Temporal Appearance and the Local Distribution of Interest Points

DOI

10.2991/icfcce-14.2014.19How to use a DOI?

Keywords

Action recognition, BOW, SVM, Local spatio-temporal distribution

Abstract

The traditional Bag of Words (BOW) algorithm considers the frequency of visual words only, whereas it ignores their spatial and temporal correlations. Many methods have been designed to remedy this defect .In this paper, we propose a new descriptor to describe the local spatio-temporal distribution information of each point. This new descriptor, combined with HOG3D, is used to describe human actions. K-means clustering algorithm is introduced to generate codebook of visual words, achieving the integration of two features under the BOW model. Finally, Support Vector Machine (SVM) is used for action recognition. We extensively test our method on the standard Weizmann and KTH action datasets. The results show its validity and good performance.

Copyright

© 2014, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Mengmeng Lu
AU  - Liang Zhang
PY  - 2014/03
DA  - 2014/03
TI  - Action Recognition by Fusing Spatial-Temporal Appearance and the Local Distribution of Interest Points
BT  - Proceedings of the 2014 International Conference on Future Computer and Communication Engineering
PB  - Atlantis Press
SP  - 75
EP  - 78
SN  - 1951-6851
UR  - https://doi.org/10.2991/icfcce-14.2014.19
DO  - 10.2991/icfcce-14.2014.19
ID  - Lu2014/03
ER  -