Proceedings of the 2015 International Conference on Electrical, Computer Engineering and Electronics

Spatio-temporal feature points detection and extraction based on convolutional neural network

Authors
Chaoyu Yang, Qian Liu, Yincheng Liang
Corresponding Author
Chaoyu Yang
Available Online June 2015.
DOI
https://doi.org/10.2991/icecee-15.2015.83How to use a DOI?
Keywords
Spatio-temporal feature points detection and extraction based on convolutional neural network
Abstract
Convolutional neural network is a kind of deep learning model, but it only act on a single image generally. This paper expands the convolutional neural network, studies common spatio-temporal features detection and extraction algorithm, proposes a model for detecting and extracting spatio-temporal features based on convolutional neural network, applicates convolutional neural network in action recognition. This model use a plurality of consecutive video frames as input, extract image feature and time dimension information from sequent video frames, convolute and sub sampling alternately, extract a variety of advanced complex abstract features gradually. Experiments show that spatio-temporal convolution neural network has improved ability to classifing and learning.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Volume Title
Proceedings of the 2015 International Conference on Electrical, Computer Engineering and Electronics
Series
Advances in Computer Science Research
Publication Date
June 2015
ISBN
978-94-62520-81-3
ISSN
2352-538X
DOI
https://doi.org/10.2991/icecee-15.2015.83How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Chaoyu Yang
AU  - Qian Liu
AU  - Yincheng Liang
PY  - 2015/06
DA  - 2015/06
TI  - Spatio-temporal feature points detection and extraction based on convolutional neural network
BT  - Proceedings of the 2015 International Conference on Electrical, Computer Engineering and Electronics
PB  - Atlantis Press
SP  - 400
EP  - 403
SN  - 2352-538X
UR  - https://doi.org/10.2991/icecee-15.2015.83
DO  - https://doi.org/10.2991/icecee-15.2015.83
ID  - Yang2015/06
ER  -