The First 3DLife Summer School!

3DLife actively supported and co-organized the "Immersive and Engaging Interaction with VH on Internet (Engage)" Summer School which took place on the 13-15 September 2010 at Hotel Alex, Zermatt, Switzerland.

Engage aimed to bring together researchers working on different aspects of believable interaction with virtual humans for Future Media Internet, from analysis of media for human-computer interaction to the construction and animation of virtual humans and believable interaction with them in immersive virtual environments. The goal was to share recent advances and explore future research directions and opportunities in the field.

The Suggested topics for papers included:

  • Sensing humans for human-computer interaction
  • Construction and animation of 3D virtual characters and avatars
  • Social and emotional interaction with intelligent entities
  • Design and evaluation of autonomous embodied conversational characters
  • Intuitive multi-modal interaction
  • Social awareness and presence
  • Applications of intelligent human-computer interaction in virtual worlds, serious games, augmented/ mixed reality and robotics
  • Computer-based perception
  • Networking models for virtual environments

Selected and invited papers that were presented in the summer school will be published as a Springer LNCS State-of-the-Art Survey book.

Engage Summer School: List of Participants
13-15 September 2010, Zermatt, Switzerland
No. Name Affiliation
1 Nadia Magnenat-Thalmann University of Geneva, Switzerland
2 Daniel Thalmann Ecole Polytechnique Fédérale de Lausanne, Switzerland
3 Janusz Holst Warsaw University of Technology, Poland
4 George Papagiannakis University of Crete, Greece
5 Mustafa Kasap University of Geneva, Switzerland
6 Maher Ben Moussa University of Geneva, Switzerland
7 Stéphane Gobron Ecole Polytechnique Fédérale de Lausanne, Switzerland
8 Junghyun Ahn Ecole Polytechnique Fédérale de Lausanne, Switzerland
9 Byungju Lee Korea University, Korea
10 Benjamin Prestele Fraunhofer Institute for Telecommunications, Germany
11 Georgios Kordelas Informatics & Telematics Institute, Greece
12 Marc Growing Dublin City University, Ireland
13 Vlado Kitanovski Queen Mary, University of London, UK
14 Ulysses Bernardet Universitat Pompeu Fabra, Spain

Legend

3DLife consortium members

Other participants

LinkedInTwitterFacebookShare

The First Issue of the 3DLife Newsletter!

The first Issue of the 3DLife biannual electronic Newsletter is now available for download! Issue #1 can be found at the 3DLife website.

The Newsletter is an instrument for regular exchange of information among the 3DLife Network of Excellence (NoE) members and the research community at large. It constitutes the primary means to collect and communicate results achieved through Network activities.

The main objectives of the Newsletter are: to report activities promoted and undertaken within the NoE; to provide links between European and international initiatives in the field; and to widely disseminate information about published papers (position papers, state of the art reviews) of researchers involved in the Network. The Newsletter is a biannual electronic publication but will be also printed for distribution at the various 3DLife project events. Website users have the possibility to subscribe to the Newsletter and automatically receive each issue in their mailbox.

This first issue includes a welcome message from the project coordinator, Professor Ebroul Izquierdo, and an article by Dr Petros Daras of ITI on the links between 3DLife and the Future Media Internet initiative. Also included is news from the first six months of the project, and impressions by two of the many PhD students involved.

LinkedInTwitterFacebookShare

3DLife Challenge Within ACM MM Grand Challenge 2010!

The challenge is on! The 3DLife Challenge 2010, "Sports Activity Analysis in Camera Networks", is now live within the ACM Multimedia Grand Challenge 2010. More details of the 3DLife annual research challenge can be found at the 3DLife website. A short description of the challenge follows.

Advances in the availability and utility of cameras is rapidly changing the sporting landscape. In professional sports we are familiar with high-end camera technology being used to enhance the viewer experience above and beyond a traditional broadcast. High profile examples include the Hawk-Eye Officiating System as used in tennis and cricket or ESPN’s recent announcement to showcase 3D broadcast in its coverage of the 2010 FIFA World Cup. Whilst extremely valuable to the viewing experience, such technologies are really only feasible for high profile professional sports. On the other hand, advances in camera technology coupled with falling prices means that reasonable quality visual capture is now within reach of most local and amateur sporting and leisure organizations. Thus it becomes feasible for every field sports club, whether tennis, soccer, cricket or hockey, to install their own camera network at their local ground. In fact, the same goes for other leisure activities like dance, aerobics and performance art that take place in a constrained environment and that would benefit from visual capture. In these cases, the motivation is usually not for broadcast purposes, or for the technology to act as a “video referee” or adjudicator, but rather to facilitate coaches and mentors to provide better feedback to athletes based on recorded competitive training matches, training drills or any prescribed set of activities.

This challenge focuses on exploring the limits of what is possible in terms of 2D and 3D data extraction from a low-cost camera network for sports. Tennis is chosen as a case study as it is a sporting environment that is relatively easy to instrument with cheap cameras and features a small number of actors (players) who exhibit explosive and rapid sophisticated motion. Video data from an AV network, corresponding to 9 cameras with built in mics, installed around an indoor court capturing real athletes is provided for experimentation purposes. The capture infrastructure is deliberately set-up to model what is feasible for a local tennis club using commercial off-the shelf components i.e. 720 x 680, MPEG-4 25Hz cameras that are not calibrated or synchronized and that share only limited overlapping fields of view. We are interested in submissions that explore the limits of what is possible from such a real-world capture scenario in terms of:

  • Player localization on court and tracking through multiple camera views;
  • Event-based analysis and human behaviour modeling using multiple views of the same event / activity: one example is robustly classifying every stroke as a serve, backhand, forehand, etc considering fusion across multiple camera views; another example is detecting the game structure automatically (point, game, match).
  • 3D reconstruction of the playing arena and/or the players or their actions; an example is using player location and stroke classification to animate an avatar of the player, even coarsely;
  • Longitudinal analysis of player activity and motion over an entire training session;
  • Novel visualization and feedback mechanisms of any analysis results.
LinkedInTwitterFacebookShare