Multi-kinect skeleton fusion for enactive games

Abstract

We present a procedural method and an implementation of multi- Kinect skeleton fusion on Unity environment. Our method calibrates two Kinects by combining the relative coordinates of a user’s torso onto a single coordinate system. The method is tested with a small number of participants in scenarios involving multiple users, results indicate that the method provides an improvement over a single camera, and it is accurate enough for games and entertainment applications. The video demonstration of the system is provided, and future directions to improve accuracy are outlined.