Video segmentation using stabilized inverse diffusion

A video segmentation scheme using stabilized inverse diffusion equations is proposed. The scheme is based on the non-linear scale-space analysis of video lattice. Non-linear diffusion and especially stabilized inverse diffusion is a very robust method for image segmentation. In this paper the two-dimensional diffusion process has been extended to three dimensions. The segmentation scheme is based on this extended process. Also, a progressive scale-space evolution of the image sequence is proposed that reduces the memory requirements as well as solves the region correspondence problem. Finally, segmentation results for two image sequences are shown.