Fast Image and Video Segmentation Based on Alpha-tree Multiscale Representation

In this paper, we propose to rely on a recent image representation model, namely the alpha-tree, to achieve efficient segmentation of images and videos. The alpha-tree is a multiscale representation of an image, based on its quasi-flat zones. An in-depth study of this tree reveals some interesting features of image pixels and regions. These features are then used in the design of both automatic and interactive segmentation algorithms. Interactivity is achieved thanks to a new and efficient implementation scheme. Experiments on the Berkeley Segmentation Dataset lead to very promising results.