Spatio-temporal video object segmentation using moving detection and graph cut methods

Segmentation of video foreground objects from background has many important applications, such as human computer interaction, video compression, multimedia content editing and manipulation. From a single video sequence with a moving foreground object and stationary background, this paper propose a novel algorithm to extract video object using graph cut and moving detection methods. The key idea in our paper is to obtain the moving object region which can be set as the possibility foreground, and the other region set as background, then this prior can be used by means of graph cut, video segmentation is then transformed to static image segmentation which can be achieved by binary min-cut.