Scalable segmentation-based coding of video sequences addressing content-based functionalities

In this paper, we address video scalability in the framework of a region-based coding system, allowing content-based functionalities. The proposed algorithm can construct scaled layers from a video sequence, each one with either fixed bit-rate or fixed quality, allowing content based manipulation. Two modes of operation have been defined: a supervised mode, that allows the user to select the objects to be coded in the enhancement layer, and an unsupervised mode, where this selection is done by the algorithm itself