The focus of this workshop is on all issues related to tracking for mixed and augmented reality applications. Unlike the tracking sessions of the main conference, this workshop does not require pure novelty of the proposed methods; it rather encourages presentations that concentrate on complete systems and integrated approaches engineered to run in real-world scenarios. The research felds covered include self-localization using computer vision or other sensing modalities (such as depth cameras, GPS, inertial, etc.) and tracking systems issues (such as system design, calibration, estimation, fusion, etc.). This year's focus is also expanded to research on object detection and semantic scene understanding with relevance to augmented reality. Implementations on mobile devices and under real-time constraints are also part of the workshop focus. These are issues of core importance for practical augmented reality systems.

Optical see through head mounted displays (OST-HMD) are ever since the first days of Augmented Reality (AR) in focus of development and in nowadays first affordable and prototypes are spread out to markets. Despite common technical problems, such as having a proper field of view, weight, and other problems concerning the miniaturization of these systems, a crucial aspect for AR relies also in the calibration of such a device with respect to the individual user for proper alignment of augmentations. Our demonstrator shows a practical solution for this problem along with a fully featured example application for a typical maintenance use case based on a generalized framework for application creation. We depict the technical background and procedure of the calibration, the tracking approach considering the sensors of the device, user experience factors, and its implementation procedure in general. We present our demonstrator using an Epson Moverio BT-200 OST-HMD.

Using Head-up-Displays (HUD) for Augmented Reality requires to have an accurate internal model of the image generation process, so that 3D content can be visualized perspectively correct from the viewpoint of the user. We present a generic and cost-effective camera-based calibration for an automotive HUD which uses the windshield as a combiner. Our proposed calibration model encompasses the view-independent spatial geometry, i.e. the exact location, orientation and scaling of the virtual plane, and a view-dependent image warping transformation for correcting the distortions caused by the optics and the irregularly curved windshield. View-dependency is achieved by extending the classical polynomial distortion model for cameras and projectors to a generic five-variate mapping with the head position of the viewer as additional input. The calibration involves the capturing of an image sequence from varying viewpoints, while displaying a known target pattern on the HUD. The accurate registration of the camera path is retrieved with state-of-the-art vision-based tracking. As all necessary data is acquired directly from the images, no external tracking equipment needs to be installed. After calibration, the HUD can be used together with a head-tracker to form a head-coupled display which ensures a perspectively correct rendering of any 3D object in vehicle coordinates from a large range of possible viewpoints. We evaluate the accuracy of our model quantitatively and qualitatively.

As large ships are never produced in masses, it often occurs that the construction process and production process overlap in time. Many shipbuilding companies have problems with discrepancies between the construction data and the real built ship. The assembly department often has to modify CAD data for a successful installation. We present an augmented reality system, where a user can visualize the construction data of pipes and modify these in the case of misalignment, collisions or any other conflicts. The modified pipe geometry can be stored and further used as input for CNC pipe bending machines. To guarantee an exactly orthogonal passage of the pipes through aligning bolt holes, we integrated an optical measurement tool into the pipe alignment process.

For many tasks like markerless model-based camera tracking it is essential that the 3D model of a scene accurately represents the real geometry of the scene. It is therefore very important to detect deviations between a 3D model and a scene. We present an innovative approach which is based on the insight that camera tracking can not only be used for Augmented Reality visualization but also to solve the correspondence problem between 3D measurements of a real scene and their corresponding positions in the 3D model. We combine a time-of-flight camera (which acquires depth images in real time) with a custom 2D camera (used for the camera tracking) and developed an analysis-by-synthesis approach to detect deviations between a scene and a 3D model of the scene.

Augmented Reality (AR) is a technology which has become very popular in the last years. In this context also the idea of using of AR for training applications has become very important. AR offers a large potential for training only if the training is well focused to the skills that have to be trained and if the training protocol is well designed. On the other hand, the generation of the training content to be transferred via AR is a comprehensive problem that is addressed in this paper. Thus, this paper tries to describe the whole chain of implementations and general aspects involved in the creation of AR training applications, including examples for used multimodal devices. This chain starts with the capturing of expert actions to be hold in the "digital representation of skill". The digital representation of skill is transferred to the training protocol that specifies the storyboard of the AR training session. The paper includes two different implementations of AR training systems and describes the general idea of informational abstraction from low level data up to interaction and from design to application.

This paper presents a simple yet effective approach for classification of human postures by using a time-of-flight camera. We investigate and adopt linear projection techniques such as Locality Preserving Projections (LPP), Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA), which are more widespread in face recognition and other pattern recognition tasks. We analyze the relations between LPP and LDA and show experimentally that using LPP in a supervised manner effectively yields very similar results as LDA, implying that LPP may be regarded as a generalization of LDA. Features for offline training and online classification are created by adopting common image processing techniques such as background-subtraction and blob detection to the time-of-flight data.

Since the last ten years product development in automotive industry is changing radically. Most physical mock-ups have vanished and are now replaced by digital ones. But they are still needed for final evaluations or issues, which cannot be adequately simulated. During their production, deviations from the CAD model may be made. Since digital and real mock-up must match for the further product development, the transfer of differences between physical and digital mock-up to the CAD format is a crucial issue. In this paper an augmented reality (AR) based tool-chain is presented, which allows matching the CAD data with real mock-ups and documents the differences between them. Essential functions like measurement and online construction are provided, allowing the end-users to create information in AR space and feeding them back into the CAD model.

One of the key requirements of augmented reality systems is a robust real-time camera pose estimation. In this paper we present a robust approach, which does neither depend on offline pre-processing steps nor on pre-knowledge of the entire target scene. The connection between the real and the virtual world is made by a given CAD model of one object in the scene. However, the model is only needed for initialization. A line model is created out of the object rendered from a given camera pose and registrated onto the image gradient for finding the initial pose. In the tracking phase, the camera is not restricted to the modeled part of the scene anymore. The scene structure is recovered automatically during tracking. Point features are detected in the images and tracked from frame to frame using a brightness invariant template matching algorithm. Several template patches are extracted from different levels of an image pyramid and are used to make the 2D feature tracking capable for large changes in scale. Occlusion is detected already on the 2D feature tracking level. The features' 3D locations are roughly initialized by linear triangulation and then refined recursively over time using techniques of the Extended Kalman Filter framework. A quality manager handles the influence of a feature on the estimation of the camera pose. As structure and pose recovery are always performed under uncertainty, statistical methods for estimating and propagating uncertainty have been incorporated consequently into both processes. Finally, validation results on synthetic as well as on real video sequences are presented.

We present a real-time model-based line tracking approach with adaptive learning of image edge features that can handle partial occlusion and illumination changes. A CAD (VRML) model of the object to track is needed. First, the visible edges of the model with respect to the camera pose estimate are sorted out by a visibility test performed on standard graphics hardware. For every sample point of every projected visible 3D model line a search for gradient maxima in the image is then carried out in a direction perpendicular to that line. Multiple hypotheses of these maxima are considered as putative matches. The camera pose is updated by minimizing the distances between the projection of all sample points of the visible 3D model lines and the most likely matches found in the image. The state of every edge's visual properties is updated after each successful camera pose estimation. We evaluated the algorithm and showed the improvements compared to other tracking approaches.