Uwe Kowalik

BROAFERENCE: a next generation multimedia terminal providing direct feedback on audience’s satisfaction level

In this paper we present BROAFERENCE, a test bed for studying future oriented multimedia services and applications in distributed environments. The BROAFERENCE system provides a method of direct feedback of audience satisfaction level by means of real-time smile-detection. We describe the realtime system components and we will show the result of our approach to record and transmit the data of smile intensity as a hint for “how much the audience enjoys” the TV program.

BROAFERENCE: A Prototype of an Emotion-based TV Quality Rating System

Whether a television (TV) program is good or not is generally judged by its TV rating, which indicates the audience size. However, it is obvious that a TV rating does not necessarily guarantee the quality of the program. In this chapter, we describe the architecture and experimental results of BROAFERENCE, which is an emotion-based TV quality rating system that makes it possible to judge the quality of a TV program by measuring emotional information from the TV audience. BROAFERENCE utilizes automatic detection of facial expressions and gaze information via a camera observing the TV program’s audience in order to collect emotional cues about the impact of a certain program as well as measuring the attention of viewers.

BROAFERENCE: using emotion data in multimedia services

During the last years a big step towards the worldwide introduction of digital TV has been done. In September 2000 the Multimedia Home Platform (MHP) was launched at IBC as an approach for a unified multimedia platform that is not only capable of presenting digitally transmitted TV programs but also changes the tenets of television from simply consuming a program towards interactive contents enriching the audience’ TV experience by providing means for new and attractive services using e.g. a back channel. Against this background we present BROAFERENCE – a study on next generation multimedia terminal. BROAFERENCE provides a video chat feature for people who are watching the same TV channel at the same time. Users can lookup others and build ad hoc video chat groups to exchange opinions or simply enjoy the program together. Thinking about this scenario there arises the problem of how to look up other users amongst thousands of people. Even more, which are the criteria to find interesting people we want to talk to? Of course someone can use a phonebook like data base containing friends and family. But what if one would like to communicate with new people that share the same interest or have a similar nature? In the following we will present our new approach of emotion and interest based user lookup. We believe that our work will contribute to develop a communicative human society with less of the anonymity that has been introduced by common Internet technology.