ABSTRACT
The state-of-the-art in matting research has been significantly advanced by formulating matting as a graph labeling problem and solving it using graph optimization methods. This chapter considers the trimap for image matting, and focuses on how to estimate fractional alpha values in the U region. It describes describe how to generate temporally consistent trimaps for video frames, as it is the main bottleneck for applying matting techniques in video. The chapter shows that many image matting approaches share a rather common graph structure, and the merit of each method lies in its unique way to define the edge and node weights in the graph. In difficult cases where the foreground and background regions contain high contrast textures, most existing matting approaches may not work well, since their underlying color smoothness assumptions are violated. A good video matting system has to provide accurate mattes on each frame. More importantly, the alpha mattes on adjacent frames have to be temporally coherent.
