An Interactive Control System for 3D Display Using Hidden Markov Model

DOI

10.2991/icmt-13.2013.95How to use a DOI?

Keywords

Gesture Recognition, HMM, 3D display.

Abstract

This paper describes a system fulfilling interactive 3D-TV control. The system captures the position of the users’ right hand, and then records and feature-extracts the trajectory of the gestures. After that, the movement of the users’ input gestures can be recognized for interactive 3D-TV operations such as rotating a 3D object. In the system, the recognition of trajectory consists of three stages: the training of models, the pre-process of data and the estimation of gestures. Hidden Markov Model (HMM) with Left-Right Bounded (LRB) structure is used in the training and estimation while an improved direction coding is proposed to extract features. Besides, the methods of two-dimension filtering and corner detection are designed for the segmentation of gestures. The system can be applied to many applications (e.g. 3D game) with the gesture control section.

Copyright

© 2013, 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  - Xu Liujing
AU  - Cao Xun
AU  - Deng Xiangdong
AU  - Wang Yuanqing
AU  - Jin Jing
PY  - 2013/11
DA  - 2013/11
TI  - An Interactive Control System for 3D Display Using Hidden Markov Model
BT  - Proceedings of 3rd International Conference on Multimedia Technology(ICMT-13)
PB  - Atlantis Press
SP  - 764
EP  - 771
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmt-13.2013.95
DO  - 10.2991/icmt-13.2013.95
ID  - Liujing2013/11
ER  -