Research groups

Research Priorities

Augmented Reality (AR) can provide a new class of user interface experiences, in particular for mobile computing. AR is still a young research field and hence strongly driven by basic research and experimental methods. The true appeal of AR lies exactly in its deployment as a mobile user interface, available anytime and anywhere.

In the field of localization and tracking, AR requires tracking of the camera pose and the pose of objects in the environment, with high accuracy, six degrees of freedom and in real-time. It is also required that this works on a global scale and preferably with no or only minimal infrastructure. The primary approaches to achieve all this are computer vision techniques. The Mobile Augmented Reality research group also considers fusion with other sensors, such as inertial measurement units, or GPS if available. While many techniques for tracking in AR have been investigated in the last years, no single method is generally applicable, and many methods that deliver good performance do so only under constraining assumptions. What is more severe, an increase in efficiency of orders of magnitude is needed to make the more efficient techniques applicable on mobile devices.

In the field of rendering and visualization, AR requires photorealistic synthesis of video and real images. In addition, situated visualization are required: The AR display should highlight context-sensitive important information, reveal occluded, imperceptible or invisible information, provide evidence of the available 3D user interface widgets embedded into the real environment and feedback for the consequences of user interactions with such widgets. All of this must make take perceptual capabilities and limitations of the human user into account.

In the field of interaction, AR as a three-dimensional medium: Given appropriate knowledge of the physical environment, our Mobile Augmented Reality research group can build a spatial interface for interacting naturally with the real world. We are only now starting to explore the true power of such interaction based on the recent technical developments such as real-time tracking that make the deployment practical. Naturally, all claims about the usability of interaction methods must be evaluated with real users 

References

• Graz University of Technology
• AVL List Gmbh