Narrow Results

Natural human-computer interaction is an active research topic in the field of computer vision with widespread applications and one important application is in computer game. In this paper, we propose a novel method using forearm gesture as the input of the Tetris game via an ordinary camera. We use the particle filter to track the movement of the forearm and thus obtain directional information. Thereafter, the directional information is mapped into the input of the Tetris game. In comparison with existing human-computer interaction (HCI) systems which require expensive equipment such as stereo cameras, our system only requires an ordinary camera. Experimental results demonstrate that our method effectively tracks the movement of a human forearm, and implement real-time control for the Tetris game.