Adaptive graph-cut algorithm to video moving objects segmentation based on Euler's Elastica Model

The traditional graph-cut algorithm to video moving objects segmentation is based on the low-order MRF. The detected moving objects will be over-smoothing. In this paper, an adaptive graph-cut algorithm to video moving objects segmentation based on Euler's Elastica Model was proposed. The higher-order moving objects model is used to restrict the shape of moving object. Experimental results show that the proposed method can effectively and stably segment moving objects from the video and can preserve sharp and detail features better than the traditional graph-cut algorithm.