Robust Silhouette Extraction from Kinect Data

Michele Pirovano, Carl Yuheng Ren, Iuri Frosio, Pier Luca Lanzi, Victor Adrian Prisacariu, David William Murray, N. Alberto Borghese

Abstract: Natural User Interfaces allow users to interact with virtual environments with little intermediation. Immersion becomes a vital need for such interfaces to be successful and it is achieved by making the interface invisible to the user. For cognitive rehabilitation, a mirror view is a good interface to the virtual world, but obtaining immersion is not straightforward. An accurate player profile, or silhouette, accurately extracted from the real-world background, increases both the visual quality and the immersion of the player in the virtual environment. The Kinect SDK provides raw data that can be used to extract a simple player profile. In this paper, we present our method for obtaining a smooth player profile extraction from the Kinect image streams.