SEGMENTATION OF VIDEO SEQUENCES FOR PARTITION TREE GENERATION

In this paper we propose a segmentation structure to generate a partit ion tree with multiple partition proposals. These multiple partitions are obtained for every image in a hierarchical way, front the coarsest one to the finest one, Time evolution of the regions is defined throu gh a projection step which relates the previous coded partition with t he current partition tree, Finer partitions than the projected one are defined segmenting the projected partition using texture criteria, wh ile coarser partitions are obtained merging regions with motion criter ia. Morphological tools are used both in the projection and the re-seg mentation steps.