DOI: 10.5176/2251-1679_CGAT23

Authors: Nicholas Hadjiminas and Christopher Child


As technology evolves, more interactive video game controllers are being developed in order to provide players with greater interaction with games. Motion control is one of the most challenging and exciting topics in today's games industry and the related controllers have taken the industry by storm becoming a prerequisite for new generation game consoles. We propose a new method to quickly and accurately recognize human motion using skeletal relation angle recognition rather than body parts Cartesian co-ordinates position recognition in order to provide a more flexible, accurate and efficient way tracking human motion. This method was used to develop a tool kit that aims to help game designers easily identify and recognise a user’s pose and gestures using Microsoft’s Kinect motion controller, in order to then link these movements with actions in a game for example key presses can be liked to poses or gestures in order to produce key events. Finally, we evaluated the usability of the tool kit and the success rate of skeletal relation angle recognition through an experiment. Ten representative users were selected and asked to complete a set of tasks using the “Be the Controller” project and a game (World of Warcraft) in order to simulate real conditions of use of the software and evaluate its usability. The data from this experiment helped to form some important conclusions: users found it easy to create their own poses and gestures; they were enthusiastic about the fact that they were able to bind their actions to key/mouse events; and were satisfied with the success rate of pose recognitions

Keywords: Pose and gesture recognition; Kinect project; Be the controller tool kit;motion control; human motio; skeletal relational angles recognition

Price: $4.99

Loading Updating cart...