Robust visual hand pose estimation and tracking matching inverse kinematics on synergistic subspaces

In this thesis a solution to the problem of recovering and tracking the 3D position, orientation and full articulation of a human hand from markerless visual observations obtained with a range camera is developed. The 3D tracking of human hands has a number of diverse applications including but not limited to human activity recognition, human-computer interaction, understanding human grasping, robot learning by demonstration , etc. The method is based on an inverse kinematics scheme. The high dimensionality of the estimation problem is reduced by using the PCA (Principal Component Analisys) on a large dataset of human hand poses. The proposed method does not require special markers and/or a complex image acquisition setup. Being model based, it provides a continuous solution to the problem of tracking hand articulations