Hand tracking by extending distance transform and hand model in real-time

Abstract

Tracking a human's hand is not a trivial task. This paper contributes a new approach for hand tracking based on distance transform (DT) and edge points in real-time. In the beginning, we create a hand model geometrically in three dimensions. It is done by utilizing shortened quadrics. After that, the degrees of freedom, shortly called as DOF, for every joint angle correspond to each DOF to use in the later process. The edge likelihood is used for the feature extraction. A Bayesian classifier is utilized adaptively and accurately for the silhouette likelihood. For this reason, it is to cope greatly with any environmental changes visibly. By using these techniques, this method can be performed in real-time. Experimental results are provided.