SEGMENTATION-BASED VIDEO CODING SYSTEM ALLOWING THE MANIPULATION OF OBJECTS

This paper presents a generic video coding algorithm allowing the cont ent-based manipulation of objects. This manipulation is possible thank s to the definition of a spatiotemporal segmentation of the sequences. The coding strategy relies on a joint optimization in the rate-distor tion sense of the partition definition and of the coding techniques to be used within each region. This optimization creates the link betwee n the analysis and synthesis parts of the coder. The analysis defines the time evolution of the partition, as well as the elimination or the appearance of regions that are homogeneous either spatially or in mot ion. The coding of the texture as well as of the partition relies on r egion-based motion compensation techniques, The algorithm offers a goo d compromise between the ability to track and manipulate objects and t he coding efficiency.