Hand pose estimation from a single RGB-D image

Abstract

Hand pose estimation is an important task in areas such as human computer interaction (HCI), sign language recognition and robotics. Due to the high variability in hand appearance and many degrees of freedom (DoFs) of the hand, hand pose estimation and tracking is very challenging, and different sources of data and methods are used to solve this problem. In the paper, we propose a method for model-based full DoF hand pose estimation from a single RGB-D image. The main advantage of the proposed method is that no prior manual initialization is required and only very general assumptions about the hand pose are made. Therefore, this method can be used for hand pose estimation from a single RGB-D image, as an initialization step for subsequent tracking, or for tracking recovery. © 2013 Springer-Verlag.