A novel approach for moving object segmentation used in dynamic scene

A novel video moving object segmentation algorithm based on global motion compensation and non-parametric kernel density estimation is proposed in this paper. Firstly, an efficient and accurate global motion compensation method is used to remove the motion of background. Then the non-parametric kernel density estimation is applied to establish foreground/background probability models. Lastly, the moving object can be obtained by comparing the foreground/background probability and morphological postprocessing. Experimental results demonstrate that the proposed algorithm has good results and reduces the complexity of moving object segmentation in dynamic scene.