Supervised video object segmentation using a small number of interactions

In this paper, a supervised video object segmentation algorithm using a small number of interactions is proposed. The proposed algorithm is composed of three steps: semi-automatic first frame segmentation, automatic object tracking and boundary refinement. Homogeneous region segmentation is performed before the user interaction for the first frame to minimize the amount of interaction. Then, a polygon with very few key nodes can be drawn conveniently to get the segmentation mask of the first frame. In the object region tracking, pixel-wised backward tracking is adopted. Finally, a method for the mask refinement is proposed by considering similar pixels of each pixel in its neighbor region. Extensive experimental results show that the proposed algorithm is effective for video object segmentation semiautomatically.