| | |
Summary: Department of Computer Science
University of Crete, Greece
and
Institute of Computer Science
Foundation of Research and Technology { Hellas (FORTH)
Heraklion, Crete, Greece
Parallelism can be exploited to handle the enormous
computational requirements of many vision appli-
cations. However, the computational power oered
by multiprocessor architectures cannot be fully har-
nessed to achieve the desired speedup. This is pri-
marily due to the unbalanced distribution of compu-
tational load among the processors of a parallel ar-
chitecture. Furthermore, in parallel implementations
of image analysis tasks, what constitutes computa-
tional load and the load balancing requirements of
speci c implementations are often dicult to de ne
in a systematic way. In this paper, we consider the
load balancing requirements of parallel implementa-
tions of intermediate level vision tasks on distributed
|
