The main concern in image processing is the computation cost. Markov r
andom field (MRF)-based algorithms particularly require a significant
amount of computation. The paper investigates three solutions to imple
ment a simple, but robust, MRF-based motion detection algorithm in rea
l time: SIMD machine, DSP-based image processing board, and analog res
istive network. Details and performances of each implementation are gi
ven and a comparison between each realization is made. The underlying
goal of this work is to study if real-time implementations of MRF-base
d algorithms are feasible or not. The answer is positive in the case o
f quite simple algorithms, but reserved with more complex ones. (C) 19
98 Academic Press Limited.