Object segmentation in video via graph cut built on superpixels

This paper proposes a real-time scheme for object segmentation in video. In the first stage a segmentation based on pairwise region comparison is utilized to oversegment image through extracting superpixels. Next, the algorithm applies the graph cut built on such superpixels, instead of the image pixels. Owing to the optimization is performed on a simpler graph and in consequence the object segmentation runs in shorter time. Tracking of object features over time contributes toward improved segmenting the object from one image to another. The segmentation information supports following the entire object, instead of just a few features on it. The objects are segmented correctly as complete entities, despite the high variability of the object shape and cluttered background. Experimental results illustrate the efficiency and effectiveness of the algorithm.