University of Cambridge > Talks.cam > Rainbow Interaction Seminars > Movement expressivity analysis in affective computers: from recognition to expression of emotion

Movement expressivity analysis in affective computers: from recognition to expression of emotion

Add to your list(s) Download to your calendar using vCal

  • UserDr. Ginevra Castellano, Queen Mary University of London
  • ClockThursday 13 November 2008, 14:15-15:15
  • HouseSS03.

If you have a question about this talk, please contact Laurel D. Riek.

One of the challenging issues in human-computer interaction is to endow a machine with an emotional, affective intelligence. Emotionally sensitive systems must be able to create an affective interaction with users: they must be provided with the ability to recognise, express and regulate emotions. Computers endowed with these abilities are called affective computers. This talk investigates the role of human movement expressivity as a source of affective information. It focuses on video-based analysis algorithms, techniques and approaches for using movement expressivity information for the development of different paradigms of interaction in affective computers. First, a computational approach for emotion recognition based on the expressivity of human movement is presented. Expressive motion cues (e.g., movement qualities such as the quantity of motion, fluidity, etc.) are considered as a source of affective information. A model that defines features retaining information about the temporal dynamics of expressive motion cues is proposed. Second, we present the design of an affective interaction between a user and an Embodied Conversational Agent based on movement expressivity. Movement expressivity is used to increase the user’s engagement by generating an affective loop: the user’s expressive movement is analysed in real-time and used to generate an expressive behaviour in the agent. Finally, an affective interactive system enabling users to make use of the body as an expressive interface is presented. In this system, movement expressivity is used to control the real-time generation of audio-visual feedback.

This talk is part of the Rainbow Interaction Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity