Thomas Pintaric

Towards massively multi-user augmented reality on handheld devices

Augmented Reality (AR) can naturally complement mobile computing on wearable devices by providing an intuitive interface to a three-dimensional information space embedded within physical reality. Unfortunately, current wearable AR systems are relatively complex, expensive, fragile and heavy, rendering them unfit for large-scale deployment involving untrained users outside constrained laboratory environments. Consequently, the scale of collaborative multi-user experiments have not yet exceeded a handful of participants. In this paper, we present a system architecture for interactive, infrastructure-independent multi-user AR applications running on off-the-shelf handheld devices. We implemented a four-user interactive game installation as an evaluation setup to encourage playful engagement of participants in a cooperative task. Over the course of five weeks, more than five thousand visitors from a wide range of professional and socio-demographic backgrounds interacted with our system at four different locations.

Chronic pain rehabilitation with a serious game using multimodal input

Rehabilitation for chronic pain follows a multidisciplinary approach, which despite the effort, often lacks the long term success and patients often fail to translate the skills learned in therapy to every day life. Serious games are hypothesized to support patients to self manage their complaints and keep training their physical functions by themselves, especially, when the game is controlled by the patients own body performance. In this paper we present the implementation of a system providing multimodal input, including our own full body motion capture system, a low cost motion capture system (Microsoft Kinect) and biosignal acquisition devices to a game engine. In addition, a workflow has been established, that enables the use of the acquired multimodal data for serious games in a medical environment. Finally, a serious game has been implemented, targeting rehabilitation of patients with chronic pain of the lower back and neck. The focus of this work is on the multimodal input and how it is used in a game to support rehabilitation of chronic pain patients. A brief comparison of a marker-based full body MoCap system and Microsofts Kinect is included. Preliminary results of tests currently underway are provided.

Full body interaction for serious games in motor rehabilitation

Serious games and especially their use in healthcare applications are an active and rapidly growing area of research. A key aspect of games in rehabilitation is 3D input. In this paper we present our implementation of a full body motion capture (MoCap) system, which, together with a biosignal acquisition device, has been integrated in a game engine. Furthermore, a workflow has been established that enables the use of acquired skeletal data for serious games in a medical environment. Finally, a serious game has been implemented, targeting rehabilitation of patients with chronic pain of the lower back and neck, a group that has previously been neglected by serious games. The focus of this work is on the full body MoCap system and its integration with biosignal devices and the game engine. A short overview of the application and prelimiary results are provided.

The invisible train: a collaborative handheld augmented reality demonstrator

We describe a software framework for rapidly developing and deploying self-contained, multi-user Augmented Reality applications on a variety of commercially available handheld computers (PDAs).

Augmented reality live-action compositing

This report describes a system that performs live-action compositing of physical and virtual objects to a panoramic background image in real-time at interactive rates. A static camera is directed towards a 40 cm/sup 3/ miniature stage, whose backdrop has been colored in chromatic green. Users can add virtual objects and manipulate their parameters within the scene by using a proxy device that consists of a small rod attached to a fiducial marker. Our system runs on commodity hardware such as a notebook equipped with a firewire video camera. The necessary chroma-keying and adaptive difference-matting algorithms have been implemented on a GPU using fragment shading.