Moving object segmentation based on Markov random field and active contour model

A method extracting moving object was proposed by utilizing the Markov random field(MRF) and active contour model in video sequences.Firstly,a rough motion template was obtained by motion detection based on Markov random field model and through post-processing.Secondly,after extracting the initial contour of the object,the energy function of active contour model was constructed.Finally,the solution of minimizing the energy function was obtained by using the modified greedy algorithm,after which,the precise contour of the object was extracted.The experimental results show that the proposed algorithm can effectively segment and extract moving object in video sequences.