A novel moving object segmentation algorithm based on spatiotemporal Markov random field

In the field of image processing, the segmentation of moving object in video sequences has attracted much interest in recent years. In this paper, a novel method of moving object segmentation based on spatio-temporal Markov random field is proposed. In this method, two initial label fields are firstly derived from the three successive images, after which the uniform label is obtained after the AND-operation on the two initial labels. Finally, the optimized labels are obtained with the maximum a posteriori method where the color clustered image of the original image is used as priors. The new MRF model contributes to the weakening of the noise and to the elimination of the covered-uncovered background and to the recovery of the uniform moving regions.