A novel background model based on pixel layer for moving objects detection in a dynamic scene is presented in this paper. Fast mean shift approach is used to cluster into layers where those pixels share similar statistics. The background is then modeled as a group of pixel layers. An incoming pixel is detected as foreground if it does not adhere to these layer-models of the background. The experiments show that the proposed method performs better than the traditional MoG method under dynamic background and especially in the presence of nominal camera motion.