Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)

Action Recognition Based on Cascade Feature and Multi-layer Classifier

Authors
Taizhe Tan, Chuhong Li
Corresponding Author
Taizhe Tan
Available Online May 2018.
DOI
10.2991/ncce-18.2018.146How to use a DOI?
Keywords
action recognition; multi-layer classifier; cascade feature.
Abstract

To Propose a recognition algorithm combines the feature of cascade of HOG/HOF with the multi-layer classifier. By extracting the foreground region of the video sequence and extracting the HOG feature and the HOF feature to makes up the HOG/HOF cascade feature. Then making all the HOG/HOF cascade features form a set of feature vectors. Then, to construct a multi-layer classifier consists of twice self-organizing mapping networks and a layer of supervised neural networks. Finally, all the features are classified to get the result of behavior recognition. The simulation results show the algorithm has a high recognition rate.

Copyright
© 2018, 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)

Volume Title
Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)
Series
Advances in Intelligent Systems Research
Publication Date
May 2018
ISBN
978-94-6252-517-7
ISSN
1951-6851
DOI
10.2991/ncce-18.2018.146How to use a DOI?
Copyright
© 2018, 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/).

Cite this article

TY  - CONF
AU  - Taizhe Tan
AU  - Chuhong Li
PY  - 2018/05
DA  - 2018/05
TI  - Action Recognition Based on Cascade Feature and Multi-layer Classifier
BT  - Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)
PB  - Atlantis Press
SP  - 877
EP  - 883
SN  - 1951-6851
UR  - https://doi.org/10.2991/ncce-18.2018.146
DO  - 10.2991/ncce-18.2018.146
ID  - Tan2018/05
ER  -