Augmented reality (AR) presents a variety of possibilities for industrial maintenance. However, the development of real-world AR solutions has been limited due to the technological capabilities and uncertainty with respect to safety at deployment. We introduce the approach of using AR simulation in virtual reality (VR) coupled with gaze tracking to enable resource-efficient AR development. We tested in-field AR guidance and safety awareness features in an iterative development-evaluation process with experts from the elevator maintenance industry. We further conducted a survey, utilizing actual gaze data from the evaluation to elicit comments from industry experts on the usefulness of AR simulation and gaze tracking. Our results show the potential of AR within VR approach combined with gaze tracking. With this framework, AR solutions can be iteratively and safely tested without actual implementation, while gaze data provide advanced objective means to evaluate the designed AR content, documentation usage, and safety awareness.

We demonstrate an interior design solution with advanced features, most importantly, a diminished reality feature. The diminished reality functionality takes 3D indoor structures into account and adapts to the lighting of the environment. We present two demonstrations on tablet and laptop. The iPad version utilizes touch screen for selecting removed objects from the image. It allows users to build modular furniture and it casts shadows of the virtual furniture for realistic visualization result. On laptop PC we demonstrate real time diminished reality for indoor AR with several options. Our demonstrations are optimized for interior design and indoor AR.

In augmented reality, marker-based tracking is the most common method for camera pose estimation. Most of the markers are black and white patterns that are visually obtrusive, but they can be hidden from the video using image inpainting methods. In this paper, we present a computationally efficient approach to achieve this. We use a high-resolution hiding texture, which is captured and generated only once. To capture continuous changes in illumination, reflections and exposure, we also compute a very low-resolution texture at each frame. The coarse and fine textures are combined to obtain a detailed hiding texture which reacts to changing conditions and runs efficiently in mobile phone environments.

In this paper, a multimodal system for augmented reality aided assembly work is designed and implemented. The multimodal interface allows for speech and gestural input. The system emulates a simplified assembly task in a factory. A 3D puzzle is used to study how to implement the augmented assembly system to a real setting in a factory. The system is used as a demonstrator and as a test-bed to evaluate different input modalities for augmented assembly setups. Preliminary system evaluation results are presented, the user experience is discussed, and some directions for future work are given.

In this paper, we present a method for generating a texture for hiding a marker in augmented reality applications. The texture is generated using the neighbourhood of the detected marker area in the image, which enables photorealistic results. The method presented here shows clear potential for real time use.