Adaptive Graph-cut Algorithm to Video Moving Objects Segmentation

An adaptive Graph-cut algorithm to video moving objects segmentation was proposed. By the Kalman prediction of the number of objectives pixels and objectives-background pixel-pairs, and adaptive updating of the nodes flux, the Graph-cut algorithm was successfully applied to video moving objects segmentation. It was achieve to continuous global optimization segmentation of video moving objects. Experimental results show that the quantitative detection parameters of this algorithm are performing well in complex background conditions.