Navigating in unknown big indoor environments with static 2D maps is a challenge, especially when time is a critical factor. In order to provide a mobile assistant, capable of supporting people while navigating in indoor locations, an accurate and reliable localization system is required in almost every corner of the building. We present a solution to this problem through a hybrid tracking system specifically designed for complex indoor spaces, which runs on mobile devices like smartphones or tablets. The developed algorithm only uses the available sensors built into standard mobile devices, especially the inertial sensors and the RGB camera. The combination of multiple optical tracking technologies, such as 2D natural features and features of more complex three-dimensional structures guarantees the robustness of the system. All processing is done locally and no network connection is needed. State-of-the-art indoor tracking approaches use mainly radio-frequency signals like Wi-Fi or Bluetooth for localizing a user. In contrast to these approaches, the main advantage of the developed system is the capability of delivering a continuous 3D position and orientation of the mobile device with centimeter accuracy. This makes it usable for localization and 3D augmentation purposes, e.g. navigation tasks or location-based information visualization.

This paper introduces a flexible and powerful software framework based on an off the shelf game engine which is used to develop distributed and collaborative virtual and augmented reality applications. We describe ARTiFICe's flexible design and implementation and demonstrate its use in research and teaching where 97 students in two lab courses developed AR applications with it. Applications are presented on mobile, desktop and immersive systems using low cost 6-DOF input devices (Microsoft Kinect, Razer Hydra, SpaceNavigator), that we integrated into our framework.

No abstract

Figure 1: a) Our setup featuring a depth sensor, thermal camera and head mounted display b) connected to a notebook for mobile operation. c) Real-time reconstruction of the staircase with an overlay of the thermal image. d) Mesh reconstructed from the structure of a room textured with the images of a thermal camera. ABSTRACTFire fighting remains a dangerous profession despite many recent technological and organizational measures. Sensors and technical systems can augment the performance of fire fighters to increase safety and efficiency during operation. An important aspect in that context is the awareness of location, structure and thermal properties of the environment. This paper focuses on the design and development of a mobile system, which can reconstruct a 3d model of a building's interior structure in real-time and fuses the visualization with the image of a thermal camera. In addition the position and viewing direction of the fire fighter within the model is determined and a thermal map can be generated from the gathered data, which could help an operational commander to guide his men during a mission.First tests with our system in different situations showed good results, being able to reconstruct different larger scenes and create thermal maps thereof.

Three-dimensional reconstructions of indoor environments are useful in various augmented and virtual scenarios. Creating a realistic virtual apartment in 3D manually does not only take time, but also needs skilled people for implementation. Analyzing a floor plan is a complicated task. Due to the lack of engineering standards in creating these drawings, they can have multiple different appearances for the same building. This paper proposes multiple models and heuristics which enable fully automated 3D reconstructions out of only a 2D floor plan. Our study focuses on floor plan analysis and definition of special requirements for a 3D building model used in a Virtual Reality (VR) setup. The proposed method automatically analyzes floor plans with a pattern recognition approach, thereby extracting accurate metric information about important components of the building. An algorithm for mesh generation and extracting semantic information such as apartment separation and room type estimation is presented. A novel method for VR interaction with interior design completes the framework. The result of the presented system is intended to be used for presenting a large number of apartments to customers. It can also be used as a base for purposes such as furnishing apartments, realistic occlusions for AR (Augmented Reality) applications such as indoor navigation or analyzing purposes. Finally, a technical evaluation and an interactive user study prove the advantages of the presented system.