Gerhard Reitmayr

gr281(at)cam.ac.uk

Navigation

Projects
Publications
Curriculum Vitae
Software
Home

Address

Cambridge University
Engineering Department
Trumpington Street
CB2 PZ1 Cambridge
UK

Research Projects

Natural feature tracking on mobile phones

Mobile phones are very inexpensive, attractive platforms for Augmented Reality, because they are small, ubiquitous, and generally accepted by customers. The trend to more full featured devices including large screens, cameras and new interface methods, allows for more complex interaction and algorithms to be implemented on phones.

To avoid the use of artifical visual markers, we have investigated the performance of natural feature tracking algorithms on mobile phones. A good example is the Fern feature classification approach developed at EPFL. We have modified and scaled down its data requirements to make it operate on a Nokia N95 device.

See the project page for more information.

Semi-automatic Annotations using SLAM

a user interacting with an augmented map

Augmented reality applications depend heavily on geometrical knowledge about the world to fuse computer graphics with real world environments. Recent work in real-time visual simultaneous localisation and mapping (SLAM) allows a system equipped with single camera to create a model of the user's environment without any prior knowledge. One scenario, where this is of interest, is remote collaboration in unknown environments, where a remote expert annotates a local live view to support a mobile user.

See the project page for more information.

Going Out: Tracking for Outdoor Augmented Reality

a user interacting with an augmented map

In this project we developed a model-based hybrid tracking system for outdoor augmented reality in urban environments enabling accurate, realtime overlays for a handheld device. The system combines several well-known approaches to provide a robust experience that surpasses each of the individual components alone: an edge-based tracker for accurate localisation, gyroscope measurements to deal with fast motions, measurements of gravity and magnetic field to avoid drift, and a back store of reference frames with online frame selection to re-initialise automatically after dynamic occlusions or failures.

See the project page for more information.

Augmented Maps

a user interacting with an augmented map

Paper-based cartographic maps provide highly detailed information visualization with unrivaled fidelity and information density. This project augments printed maps with digital graphical information and user interface components. These augmentations complement the properties of the printed information in that they are dynamic, permit layer selection and provide complex computer mediated interactions with geographically embedded information and user interface controls.

See the project page for more information.

Old projects

Mobile Collaborative Augmented Reality

Mobile computing is naturally complemented by Augmented Reality (AR), which superimposes computer-generated images onto a user's perception of the real world via devices such as see-through or see-around head mounted displays (HMD). As a consequence, a portable 3D information space becomes available to the user. This project investigated a variety of aspects of mobile augmented reality:

See the project site for more information.

iOrb - Unifying Command and 3D Input for Mobile Augmented Reality

Input for mobile augmented reality systems is notoriously difficult. Three dimensional visualization would be ideally accompanied with 3D interaction, but accurate tracking technology is usually not suitable for mobile use. Command input employs devices that are not suitable for 3D interaction and therefore require an additional mapping. This project present a new concept - the iOrb - that combines simple 3D interaction with command input in mobile applications.

See the project site for moreinformation.

OpenTracker

OpenTracker is an open software architecture that provides a framework for the different tasks involved in tracking input devices and processing multi-modal input data in virtual environments and augmented reality application. The OpenTracker engine is based on a data flow concept for multi-modal events. A multi-threaded execution model takes care of tunable performance. Transparent network access allows easy development of decoupled simulation models.

OpenTracker is available as Open Source from its project site.

DeepMatrix - Multi-user VRML worlds

The DeepMatrix System is a multi-user VRML application. It enables several users to share a single VRML world and interact with it as it is possible with an ordinary VRML world. Users can jump between different worlds and these jumps can be triggered in any way. VRML events are distributed between the several instances of the VRML world on the different users computers.

See Geometrek for details.

WebSET

The European IST project WebSET aims to produce a standardised suite of interactive three-dimensional educational tools, delivered across the WWW. These tools include collaborative functions within the 3D worlds accessible directly in standard web browsers. DeepMatrix (see above) served as the basis for the development of the 3D multi-user component in this project.

See WebSET Homepage for details.