Reply by April 12, 20062006-04-12
The Video Coding and Architectures research group is part of the Signal
Processing Systems department of the Eindhoven University of Technology,
The Netherlands.
The research spans areas of video analysis, image/video segmentation,
object-oriented and 3D video compression that underpin systems-oriented
research on video coding and architectures. This work pursues
state-of-the-art video functionality at high cost-efficiency (e.g. for
real-time aspects and/or mobile applications), through a combination of
novel algorithms and architectures.

Project title: Predictable Matching of Demands on Networked Architectures

This project is aiming at studying the mapping of advanced multimedia
algorithms on multiprocessor platforms. Advanced multimedia means here
studying modern video coding or corresponding processing such as content
analysis as a source for high-profile video signal processing. These
algorithms are usually heterogeneous from nature, requiring both special
signal processing techniques and memory-based processing. Object-oriented
coding, 3D video and content analysis are example topics where the signal
processing is at least one order of magnitude more complex than existing
standard algorithms. An optimal mapping of such algorithms is thus a
challenging task, which sometimes requires redesign of the algorithms
itself to obtain a high efficiency. The research will focus on selecting
advanced example algorithms that constitute an interesting application and
mapping those on a detailed multiprocessor model. Later, the research may
proceed in architecting special FPGA or co-processor subsystems to come to
more efficient system design. The management and scalability of the
application(s) will also play a role. This research is conducted in close
cooperation with Philips Research and other groups of the Eindhoven

Additional information is available at

Contact information
If you are interested please contact by email
Prof.dr. Peter H.N De With and PDEng. Milan Pastrnak
Contact information is available at and