A genetic algorithm-based segmentation of Markov random fieldmodeled images

摘要

An unsupervised method is presented for segmenting video sequencesndegraded by noise. Each frame in a sequence is modeled using a Markovnrandom field (MRF), and the energy function of each MRF is minimized bynchromosomes that evolve using distributed genetic algorithms. To improventhe computational efficiency, only unstable chromosomes corresponding tonmoving object parts are evolved. Experimental results show theneffectiveness of the proposed method