We introduce the first publicly available test dataset for outdoor handheld camera localization comprising over 45,000 real camera images of an urban environment captured under natural camera motions and different illumination settings. For all these images the dataset not only contains readings of the sensors attached to the camera, but also ground truth information on the geometry and texture of the environment and the full 6DoF ground truth camera pose. This poster describes the extensive process of creating this comprehensive dataset that we have made available to the public. We hope this not only enables researchers to objectively evaluate their camera localization and tracking algorithms and frameworks on realistic data but also stimulates further research.

Unlike dense stereo, optical flow or multi-view stereo, template-based tracking lacks benchmark datasets allowing a fair comparison between state-of-the-art algorithms. Until now, in order to evaluate objectively and quantitatively the performance and the robustness of template-based tracking algorithms, mainly synthetically generated image sequences were used. The evaluation is therefore often intrinsically biased. In this paper, we describe the process we carried out to perform the acquisition of real scene image sequences with very precise and accurate ground truth poses using an industrial camera rigidly mounted on the end-effector of a high-precision robotic measurement arm. For the acquisition, we considered most of the critical parameters that influence the tracking results such as: the texture richness and the texture repeatability of the objects to be tracked, the camera motion and speed, and the changes of the object scale in the images and variations of the lighting conditions over time. We designed an evaluation scheme for object detection and interframe tracking algorithms and used the image sequences to apply this scheme to several state-of-the-art algorithms. The image sequences will be made freely available for testing, submitting and evaluating new template-based tracking algorithms, i.e. algorithms that detect or track a planar object in an image sequence given only one image of the object (called the template).

Recent years have seen advances in many enabling augmented reality technologies. Furthermore, much research has been carried out on how augmented reality can be used to enhance existing applications. This paper describes our experiences with an AR-museum guide that combines some of the latest technologies. Amongst other technologies, markerless tracking, hybrid tracking, and an ultra-mobile-PC were used. Like existing audio guides, the AR-guide can be used by any museum visitor, during a six-month exhibition on Islamic art. We provide a detailed description of the museumpsilas motivation for using AR, of our experiences in developing the system, and the initial results of user surveys. Taking this information into account, we can derive possible system improvements.

Over the past years, a variety of augmented reality (AR)-based applications were created, to support industrial processes. Although these first demonstrator applications or prototypes cover all parts of the industrial product process (design, planning and production, service and maintenance), only a few of them actually turned into established and applied solutions. In the automotive industry, one successful field for AR-based applications is factory design and planning, metaio and Volkswagen Group Research have concerted their research work to continuously enhance a first prototype in order to create a serviceable and accepted software tool, which is tailored to the needs of AR-based factory planning processes. This paper presents the developing process of this application, the requirements analysis and the realization as a complete system. A concrete example in industry describes the usage of the system for factory planning and an outlook on future work in this area closes the document.

We present a solution for AR based repair guidance. This solution covers software as well as hardware related issues. In particular we developed a markerless CAD based tracking system which can deal with different illumination conditions during the tracking stage, partial occlusions and rapid motion. The system is also able to automatically recover from occasional tracking failures. On the hardware side the system is based on an off the shelf notebook, a wireless mobile setup consisting of a wide-angle video camera and an analog video transmission system. This setup has been tested with a monocular full-color video-see-through HMD and additionally with a monochrome optical-see-through HMD. Our system underwent several extensive test series under real industrial conditions and proved to be useful for different maintenance and repair scenarios.