| 
|
The objective of the project is to define new models and implement
advanced tools for audio-video analysis, synthesis and representation in
order to provide essential technologies for the implementation of
large-scale virtual and augmented environments.
The work is oriented to make man-machine interaction as natural as possible,
based on everyday
human communication by speech, facial expressions and body gestures. Man
to machine action will be based on coherent analysis of audio-video
channels to perform either low level tasks, or high level interpretation
and data fusion, speech emotion understanding or facial expression
classification. Machine-to-man action, on the other hand, will be based
on human-like audio-video feedback simulating a "person in the machine".
A common sw platform will be developed by the project for the creation
of Internet-based applications. A case study application will be
developed, demonstrated and evaluated.
The project activity will last three years, the first part devoted to
specifications definition and tools development, the last part dedicated
to the implementation of demo applications. Project coordination, within
WP1, will be carried out in synergy and concertation with other projects
working in similar research areas within and outside the IST program.
Most of the WPs will be activated at the beginning of the project. In
particular, WP2 will take responsibility of defining systems
specification with particular reference to the common software platform,
which will be developed later on in WP5, that will integrate all the
tools into an environment with authoring capability for the creation of
applications of shared virtual and augmented reality. Technical
workpackages WP3 and WP4 will develop a library of tools for managing
man-machine interaction with reference to man-to-machine and
machine-to-man communication, respectively. WP3 will be oriented to the
implementation of audio-video analysis tools, WP4 o the implementation
of audio-video synthesis tools. Both WP3 and WP4 will guarantee full
compliance to specifications defined in WP2. Activities in WP5 will be
focused on the integration of the developed tools into a common software
platform and on the implementation of an example of application based on
shared virtual and augmented environments.
The integrated sw platform, will be developed progressively through
upgraded releases, the first of which at the end of the first year of
project activity. Compliance with MPEG-4 and MPEG-7 will be guaranteed
by deep project commitment in the standardisation process (WP2). At
project conclusion, the InterFace consortium will organise an
International Workshop for public demonstration and dissemination of the
achieved results.
During the 3 year project, major deliverables will be produced that will
represent the actual project milestones. In particular, after the first
year, the common sw platform with integrated tools, after the second
year, the updated sw platform with added authoring functionality and, at
the third year, the implementation of a case study application, based on
the common sw platform. This last milestone will also include the
organisation of a public event with live demonstration of results.