IP Logo
distance keeper Computer Vision & Graphics  
Graphic Element West Graphic Element Middle Graphic Element East
 
Graphic Element Quadgray Start
Graphic Element Quadgray News
Graphic Element Quadgreen Organisation
  Image Communication
  Computer Vision & Graphics
  Immersive Media & 3D-Video
  Hardware Architectures & Implementations
  Embedded Systems
Graphic Element Quadgray Fields of Competence
Graphic Element Quadgray Fields of Application
Graphic Element Quadgray Alliances & Committees
Graphic Element Quadgray Products
Graphic Element Quadgray Events
Graphic Element Quadgray Staff
Graphic Element Quadgray Jobs
Graphic Element Quadgray Visitors
Graphic Element Quadgray Contact
Graphic Element Quadgray HHI Home
Group 2 Logo
 

 

This page has moved. If your browser doesn't automatically redirect to its new location,

click here 

 

 

Projects

 

 

Games@Large is a European Integrated Project funded under the 6th framework IST programme. The project targets at designing a platform for running an interactive rich content multimedia application such as games over local networks. The Fraunhofer HHI contributs to this project with low delay video and 3D graphics streaming.

 

 

In cooperation with adidas, a Virtual Mirror has been created that allows the user to view him/herself in a mirror with individually designed shoes. For that purpose, Fraunhofer HHI has developed a system that tracks the 3D motion of the left and right shoes in real time using a single camera. The real shoes are exchanged by 3D computer graphics models giving the user the impression of actually wearing the virtual shoes.

 

 

VISNET II builds on the success and achievements of the VISNET NoE to continue the progress towards achieving the NoE mission of creating a sustainable world force in Networked Audiovisual (AV) Media Technologies. VISNET II is a network of excellence with a clear vision for integration, research and dissemination plans. The research activities within VISNET II will cover 3 major thematic areas related to networked 2D/3D AV systems and home platforms. These are: video coding, audiovisual media processing, and security. VISNET II brings together 12 leading European organisations in the field of Networked Audiovisual Media Technologies. The 12 integrated organisations represent 7 European states spanning across a major part of Europe, thereby promising the efficient dissemination of resulting technological development and exploitation to larger communities.

 

 

The project GestAvatar extends the work performed in AvatarFutureUI. In cooperation with T-Systems, we have enhanced the real-time video and audio controled avatar animation system for the use in chat room scenarios. Gestures and hand motion are additionally recognized and used to drive an avatar with the motion of a user sitting in front of a camera.

 

 

The BMBF funded project VisionIC aims at the development of an intelligent vision platform including startup applications for the mass market. Within this project, the Fraunhofer HHI developed an Advanced Videophone System which enables multiple partners to meet and discuss in a virtual room. Image-based rendering techniques in combination with 3D head model animation allow head pose correction and enhances communication in comparison to traditional video conferencing systems.

 

 

VISNET is a European Network of Excellence funded under the 6th framework programme. Its strategic objectives are revolving around its integration, research and dissemination activities. VISNET aims to create a sustainable world force of leading research groups in the field of networked audiovisual (AV) media technologies applied to home platforms. The member institutions have grouped together to set up a network of excellence with a clear vision for integration, research and dissemination plans. The research activities within VISNET will cover several disciplines related to networked AV systems and home platforms.

 

 

In a second project for the the Bundesdruckerei GmbH, we have setup an array of 16 synchronized and calibrated cameras capturing people from different viewing directions and under varying illumination. Two degrees of head pose (rotation) has been covered by the camera grid while the in-plane rotation has been synthetically created by image interpolation.

 

 

In this Text2Video project, we have developed a system for the automatic conversion of SMS messages into video animations. From the written text, speech is synthesized and a 3D head model is synchronously animated. The recipient obtains a MMS message with a short video, where the chosen character reads the text. Both photorealistic images or cartoons can be selected for animation. Camera changes, additional head and eye motion as well as pitch shift enhance the variability of the output. The system is, e.g., used by digitalVanity.

For an interactive demo, please click here.

 

 

For the Deutsche Flugsicherung GmbH (German Airtraffic Control), we have created an MPEG-4 panorama from the tower of the Berlin Schönefeld airport. The interactive panorama was demonstrated at the Internationale Luftfahrt Ausstellung (ILA) in the context of the presentation of the future Berlin-Brandenburg International airport. For the creation of the virtual environment, image warping for the removal of objects and people and high dynamic range imaging techniques for local contrast adaptation were developed.

 

 

in cooperation with the Bundesdruckerei GmbH, we have constructed a multi-view camera array for the synchronous capturing of people from different viewing directions and under varying illumination. Methods for calibration, image enhancements, interpolation, and background substitution have been developed in order to create large databases of faces with calibrated known properties.

 

 

In cooperation with Bitfilm, short video clips of robots were created for the distribution on mobile phones via MMS. From 2D images of the robots, 3D models are created and animated using MPEG-4 facial animation parameters which are derived from text input. Automatic pan and zoom as well as speech alternation are applied in order to enhance the variability of the video clips.

 

 

In the project AvatarFutureUI in cooperation with T-Systems, we have developed a real-time system for the animation of avatars from video input. A camera captures the user and head and hand movements are tracked over time. MPEG-4 facial and body animation parameters are estimated which can be efficiently streamed over a network. At the receiver, an avatar is animated according to the user's motion. Lip movements are synthesized from the speech signal.

 

 

At the Image Processing Department, a hardware system for the projection of high-resolution video onto large screens has been developed. Multiple low-cost projectors are synchronized and the image parts are smoothly stitched together. Besides projection onto planar screens, the system can be utilized for the display of dynamic cylindrical panoramas. In this project, we have created high-resolution content and developed warping techniques in order to remove image distortions caused by the projection onto curved screens. The system was demonstrated at IBC 2004.