Since its introduction in 1985, there has been a lot of activity in the eld of second generation still image coding. In the last years, the approach has been extended to video coding and has been the basis for European RACE research pro jects. The objective of this paper is to summarize the main concepts underlying second generation video coding and to present the approach taken in the RACE pro ject MORPHECO in the context of segmentation-based video coding schemes. Comments and results on the evolution of the system, in the framework of the MPEG-4 SESAME proposal presented on behalf of the RACE pro ject MAVT are also outlined. In order to have a more complete paper, current state of the art in MPEG-4 activities are also summarized1. The paper ends with conclusions and new trends in the eld. A basic introduction to the main characteristics and limitations of rst generation coding will be also presented in order to have a self-contained paper. A more complete description of second generation video coding and in particular of the approach presented here can be found in34

Peer Reviewed