User profile forming based on audiovisual situation analysis in smart meeting room

Abstract

This paper discuss the problem of personal adjustment of smart room devices and forming of a user profile based on processing of multichannel audio and video streams, which register of the current situation and meeting participants behavior in the meeting room. Estimation of preference of device usage, user interface, participant role and their activity during meeting allows us to automate the processes of smart room preparation as well as manage multimedia presentation and record devices during events. 212 records were made during several meetings in the smart room with the help of the developed system of audio and video speaker localization. The accumulated experimental data allowed us to estimate the places in the room, from which the participants asked questions most of the time. The accuracy of camera pointing on speaker in the presentation zone as well as in the rows of sits estimated by participant’s face size and its position in frame during whole recording equals 90% approximately.