Development of an Autonomous Facial-Expression Monitoring System for Safe Work Environments

The purpose of this research is to develop an autonomous facial-expression monitoring system for elderly and/or disabled people who work at various kinds of facilities. The authors have established a system which follows one´s facial expression automatically. This system consists of Microsoft´s KINECT sensor and plural network cameras. The KINECT sensor has the ability to detect a subject´s posture and skeletal position in three dimensions. At least two network cameras are autonomously controlled so as to follow the subject´s face from different directions while walking around in the work space. The rest of the network cameras follow the subject´s activities by zoom out viewing. Field experiments were conducted in the Plant Factory Research Centre of Osaka Prefecture University, Japan. A disabled person´s face was followed by the system during work, and its effectiveness and validity demonstrated.