Research Projects

SMART VIDENTE focuses on research on the next-generation field information system for utility companies, providing mobile workforces with capabilities for on-site inspection and planning, data capture and as-built surveying. For achieving this aim, handheld Augmented Reality technology is used for on-site modification and surveying of geometric and semantic attributes of geospatial 3D models on the user’s handheld device. The project aims at providing a fully functional handheld Augmented Reality device for utility field workers. To achieve this goal, we require a software solution that can visualize registered three-dimensional underground models in real time. Registration in 3D requires being able to perform accurate global localization and posing tracking in real time without relying on unrealistic assumptions concerning prior scene knowledge. We will address this issue through fusion of vision, inertial and GPS sensors. Visualization requires the rendering of complex 3D models of underground infrastructure in a way that is easily comprehensible and useful to the mobile worker. This requires visualization techniques for geometric as well as non-geometric information from the geo-database, in particular of hidden objects through so-called “X-ray vision”. These visualization techniques need to be adaptive to scene complexity and environmental conditions. The three-dimensional geometry to be shown is not available per default, but must be extracted from a conventional database system and interpreted on-the-fly as a 3D visualization using procedural modeling techniques. We want to support annotation and even surveying tasks in the field, so the system must also allow to write information back to the geo-database. Finally, we will work with three large Austrian infrastructure companies to assess the usability of our solutions.

Precise indoor localisation is an important issue for Augmented Reality. The two major ingredients necessary to experiment with "location aware" Augmented Reality applications are

• modelling an accurate 3D model of the environment and
• tracking

The localized device is often held by an individual, allowing applications to interact with the physical environment. Various Augmented Reality setups have been build during this project. Additionally work is shown to answer the question how to accurately and rapidliy survey an indoor environment. Next to manual strategies there automated aproaches of surveying are shown. Furthermore hybrid tracking approaches are demonstrated where heterogeneous tracking sensors are attached to handheld devices (UMPCs, micro PCs). In this context the sensor data is fused, which leads to a seamless tracking experience.