No abstract

M PEG-4 defines a multimedia system for interoperable communication of complex scenes containing audio, video, synthetic audio, and graphics material. In part 1 of this two-part article (in the previous issue) we provided a comprehensive overview of the technical elements. Here in part 2 we describe an application scenario based on digital satellite television broadcasting, discuss the standard's envisaged evolution, and compare it to other activities in forums addressing multimedia specifications. The first MPEG-4 demo over satellite In April 1997 the Systems subgroup founded an implementation ad hoc group (IM1) with the mandate of validating the concepts of the MPEG-4 standard and promoting it by developing demonstration applications. This group also contributes to part 5 of the standard, the reference software. A system architecture was developed and successfully demonstrated at the 45th MPEG-4 meeting, where the world's first real-time display of MPEG-4 content (multicast over satellite) was shown to the MPEG community and the world press. Here we give a concise description of the architecture and demo mock-up. MPEG-4 broadcast scenario The scenario is an electronic programming guide (EPG) application where the user can choose among channels providing CD-quality audio, films, and news. The content is premultiplexed and then streamed. The target band for the overall application is 5 megabits per second. The overall system is constructed of a single (logical) origination point, a real-time, unidirectional communication channel, and a large number of end-user receiver/decoder terminals. It is a oneto-many, or possibly a few-to-many, system. The asymmetry of the architecture leads to an emphasis on reducing complexity and cost at the receiving side even if this implies increasing the complexity and cost at the transmitting side. The architecture is schematically depicted in Figure 1. The demonstration consisted of MPEG-4 server components located in Sunnyvale, California linked via a hybrid satellite network to MPEG-4 clients in Atlantic City, New Jersey. MPEG-4 takes advantage of the latest compression technologies, providing rendering of multiple objects within one viewing window. The network uses the Internet Group Multicast Protocol (IGMP) to route 76

This paper' provides an overview of the activities that have led to the development of a prototype application of a "talking head" compliant with MPEG-4 spectfication. The work done so far Jits in the context of one of the recent work-items defined by the ISOBEC JTCI/SC29/WGll worldwide known as MPEG. This IS0 Working Group is now in the process of defining a unifying framework where natural and synthetic audiovisual objects can be combined and rendered as a unique bouquet of synchronised interactive media. The developed facial animation system implements the following features: animation of predefined / downloaded face models, animation of face models driven either by speech synthesis applications or by MPEG-4 animation parameters. To improve photo-realism, face models can be texture mapped and calibrated according to the countenances of real people.

No abstract