An pipeline for reconstructing the 3D face model from an uncontrolled video sequence is presented which involves three major steps. Firstly, a generic deformable 3D face model is built from the 3D scans of one hundred individuals. Secondly, the 3D face shape from a video sequence is constructed by estimating poses of images using structure-from-motion technique and dense correspondences between those images by employing Huber-L1optical flow algorithm. Finally, the generated generic deformable 3D face model can be fitted to the reconstructed 3D face-shape from a video sequence provided that the deviation from the real 3D face is less than certain thresholds. The application is developed to reconstruct the 3D face-shape in nearly uncontrolled environment so the results cannot be expected to be very accurate. We discuss the steps taken to perform the first and second steps. The factors affecting the depth estimation in face region cause major accuracy problems. They are analyzed and possible improvements to enhance the 3D face-shape reconstruction are presented.

This work presents a concept for the composition of tracking systems in the context of virtual and augmented reality (VR/AR) applications. Several independent 6 DOF tracking systems can be used simultaneously to accomplish the interaction requirements for a given application. The control unit for tracking systems, processing measurements with optional properties as time stamps and quality values is described as well as procedures for the coordinate system alignment of different tracking systems and the configuration of such a hybrid system. Considerations on the way accuracy errors might increase or decrease by combining tracking systems are included. The concept is motivated considering a medical AR system combining optical and electromagnetic tracking technology as example.

This paper presents an approach to use a semitransparent display as a kind of window into a patient in the context of medical augmented reality (AR) applications. Besides the presentation of the non-off-the-shelf display, the tracking aspects of such an application are the focus of the work presented. In order to allow augmentations of real objects by virtual ones on the display, the user (i.e. physician), the display, the object (i.e. patient) and optional instruments have to be tracked. If required, a tracking system consisting of more than one subsystem, e.g. optical tracking combined with electromagnetic tracking, is used to satisfy all the needs of such a medical application.