Falling-Action Analysis Algorithm Based on Convolutional Neural Network

DOI

10.2991/ceie-16.2017.5How to use a DOI?

Keywords

Falling-Action Analysis; Deep Learning; Convolutional Neural Network

Abstract

This paper proposes a deep learning method - convolutional neural network to analyze human falling-action in video surveillance, so that we can recognize the falling-action of human body accurately in the shortest time. Firstly, vibe algorithm is used to extract the foreground and some methods of image preprocessing are employed to optimize the moving target. Then the moving target is fed into the convolutional neural network which extracts the features of various actions (including sitting, crouching, bending, falling) and classifies these actions. It is proved by experiments that our method is accurate and competitive compared with the current method to falling-action recognition.

Copyright

© 2017, 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  - Wei Liu
AU  - Jie Guo
AU  - Zheng Huang
AU  - Weidong Qiu
PY  - 2016/10
DA  - 2016/10
TI  - Falling-Action Analysis Algorithm Based on Convolutional Neural Network
BT  - Proceedings of the International Conference on Communication and Electronic Information Engineering (CEIE 2016)
PB  - Atlantis Press
SP  - 37
EP  - 42
SN  - 2352-5401
UR  - https://doi.org/10.2991/ceie-16.2017.5
DO  - 10.2991/ceie-16.2017.5
ID  - Liu2016/10
ER  -