Video Based Motion Capture System as Intuitive Interface

This paper proposes a video based motion capture system using one video camera and simulates its use as an intuitive interface for interactive 3D games. Since conventional video based motion capture systems need many cameras and take a long time to deal with many video images, they cannot generate motion data in real time. Therefore they cannot be used as a real-time input device for a standard PC. To deal with this problem, the authors have already proposed a motion capture system using one video camera (Akazawa et al., 2002a). It takes video images of the upper part of the body of a person and generates upper body motion data, e.g., x, y, z position of hands, a face rotation, etc. Since the system employs a very simple motiontracking algorithm, so it generates such upper body motion data in real time. This paper focuses on the tracking of hands’ motion on the top of a desk, and proposes the use of its motion data as 3D game input. The authors have already proposed a constructive visual 3D software development system called IntelligentBox and shown its usefulness for development of interactive 3D games (Okada and Tanaka, 1995, Okada and Itoh 2000). This paper mainly describes how the video based motion capture system works as an intuitive interface for 3D games developed using IntelligentBox.