Abstract

Keynote.- Ambient Intelligence 2.0: Towards Synergetic Prosperity.- Sensing.- Behavior Analysis Based on Coordinates of Body Tags.- MobiDiC: Context Adaptive Digital Signage with Coupons.- Slice&Dice: Recognizing Food Preparation Activities Using Embedded Accelerometers.- Reasoning and Sensing.- The Ambient Tag Cloud: A New Concept for Topic-Driven Mobile Urban Exploration.- Constructing Topological Maps of Displays with 3-D Positioning Information.- Activity Recognition for Personal Time Management.- Getting Places: Collaborative Predictions from Status.- Ambient Technology.- Place Enrichment by Mining the Web.- Sensor-Based Human Activity Recognition in a Multi-user Scenario.- Amelie: A Recombinant Computing Framework for Ambient Awareness.- Bug-Free Sensors: The Automatic Verification of Context-Aware TinyOS Applications.- Semi-automatic Story Creation System in Ubiquitous Sensor Environment.- SAGE: A Logical Agent-Based Environment Monitoring and Control System.- Using Video with Active Markers.- Ambient Assisted Living.- An Event-Driven Approach to Activity Recognition in Ambient Assisted Living.- EMon: Embodied Monitorization.- Interoperation Modeling for Intelligent Domotic Environments.- Intertwining Implicit and Explicit Awareness of Wellbeing to Support Peace of Mind and Connectedness.- NICA: Natural Interaction with a Caring Agent.- Applications and Studies.- Ambient Rabbits Likeability of Embodied Ambient Displays.- Contextual Interaction Design: The Case of Pause Buddy.- Creating a Development Support Bubble for Children.- I Bet You Look Good on the Wall: Making the Invisible Computer Visible.- AmIQuin - An Ambient Mannequin for the Shopping Environment.- Designing an Awareness Display for Senior Home Care Professionals.- Methods and Tools.- A Framework to Develop Persuasive Smart Environments.- Measuring the Response Bias Induced by an Experience and Application Research Center.- The Assisted User-Centred Generation and Evaluation of Pervasive Interfaces.- Reasoning and Adaptation.- Increased Robustness in Context Detection and Reasoning Using Uncertainty Measures: Concept and Application.- Synthetic Training Data Generation for Activity Monitoring and Behavior Analysis.- Adaptive User Profiles in Pervasive Advertising Environments. Document type: Part of book or chapter of book

Abstract

For Augmented Reality to succeed in industrial appliances, industries demand not only robust and reliable tracking techniques, but also a scalable and performant pipeline, that is easy-to-integrate within the existing data- and content environment and that enables vendors to create tracking solutions on their own. In our demo, we present recent advances of our model tracking pipeline and tracking technology, which on the one hand is easy use and easy to integrate, while on the other hand robust enough during difficult environmental conditions and which delivers high accuracy for the industrial domain. We showcase our results inside an AR-manual scenario.

Abstract

Real-time object recognition on low-power embedded devices is a widely requested task, needed in manifold applications. However, it is still a demanding challenge to achieve desired performance goals. For example, for advanced driver assistance systems (ADAS) or autonomously driven cars, object recognition and lane detection are indispensable tasks. Another field of application is the continuous retrieval of the construction progress on-site for validation of the construction site status, by detecting installed components using a given CAD model. This paper presents a framework for highly customizable object detection systems implemented on a single heterogeneous computing chip leveraging FPGA logic and standard processors. The FPGA logic is used to implement a custom variation of the Hough Transform and further image processing tasks efficiently. The dedicated logic is supplemented with a software stack, which consists of a Linux operating system, including hardware access drivers, as well as high-level libraries like OpenCV and Robot Operating System (ROS) - all running on the same device. The capabilities of the system are demonstrated for three application scenarios, namely race track recognition, lane recognition and object detection tasks performed within a construction assistance system.