Proceedings of the 2016 2nd International Conference on Artificial Intelligence and Industrial Engineering (AIIE 2016)

An Approach for Detecting Human Posture by Using Depth Image

Authors
Xianshan Li, Maoyuan Sun, Xiuxiu Fang
Corresponding Author
Xianshan Li
Available Online November 2016.
DOI
https://doi.org/10.2991/aiie-16.2016.60How to use a DOI?
Keywords
kinect; depth image; human posture; regional growth
Abstract

This paper introduces a method that can detect human posture by using depth image. The method uses head model to locate the human position which includes edge extraction, template matching and human detection. Then we extract the HOG feature from the depth images to get the characteristic vector of the original image. At last, a generalized regression neural network is processed to classify and identify the human posture. Experiments show that our method is able to identify the human posture from a depth image with a satisfactory recognition rate.

Copyright
© 2016, 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 2016 2nd International Conference on Artificial Intelligence and Industrial Engineering (AIIE 2016)
Series
Advances in Intelligent Systems Research
Publication Date
November 2016
ISBN
978-94-6252-271-8
ISSN
1951-6851
DOI
https://doi.org/10.2991/aiie-16.2016.60How to use a DOI?
Copyright
© 2016, 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  - Xianshan Li
AU  - Maoyuan Sun
AU  - Xiuxiu Fang
PY  - 2016/11
DA  - 2016/11
TI  - An Approach for Detecting Human Posture by Using Depth Image
BT  - Proceedings of the 2016 2nd International Conference on Artificial Intelligence and Industrial Engineering (AIIE 2016)
PB  - Atlantis Press
SP  - 257
EP  - 261
SN  - 1951-6851
UR  - https://doi.org/10.2991/aiie-16.2016.60
DO  - https://doi.org/10.2991/aiie-16.2016.60
ID  - Li2016/11
ER  -