Recognition of Human Action for Game System

摘要

Using human action, playing a computer game can be more intuitive and interesting. In this paper, we present a game system that can be operated using a human action. For recognizing the human actions, the proposed system uses a Hidden Markov Model (HMM). To assess the validity of the proposed system we applied to a real game, Quake Ⅱ. The experimental results verify the feasibility and validity of this game system.This system is currently capable of recognizing 13 gestures, corresponding to 20 keyboard and mouse commands for Quake Ⅱ game.