Human-computer interaction system for hand recognition based on depth information from Kinect sensor

DOI

10.2991/icmse-15.2015.62How to use a DOI?

Keywords

Human-computer interaction; Depth information; Skin color detection; Kinect sensor

Abstract

Over the past few years, people demands human-computer interaction system with more intelligent function, such as gesture recognition and motion recognition. This paper acquires color and depth information from Kinect sensor in order to capture hand motion and interact with the computer game. By using skin color detection, binarization and frame difference on color information, hand 2D information can be extracted and non-moving part will be filtered; Through mapping the hand 2D information onto the depth information, we can extract the depth information of hand; By means of them, 3D coordinates of hand can be calculated; According to the change of coordinates of several continued frames, we can extract the motion characteristic of hand and determine whether or not to meet game’s requirement which can achieve human-computer interaction. Experiment results shows that this system can recognize hand motion and interact with game effectively. This system has wide application prospect which can not only utilize in entertainment, but also has wide application value in security and medical treatment.

Copyright

© 2015, 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  - Yangtai Shen
AU  - Qing Ye
PY  - 2015/12
DA  - 2015/12
TI  - Human-computer interaction system for hand recognition based on depth information from Kinect sensor
BT  - Proceedings of the 2015 6th International Conference on Manufacturing Science and Engineering
PB  - Atlantis Press
SP  - 335
EP  - 341
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmse-15.2015.62
DO  - 10.2991/icmse-15.2015.62
ID  - Shen2015/12
ER  -