Fall Detection Application for the Elderly in the Family Heroes System

Population aging is a considerable challenge for a global society. Indeed, it raises several concerns and gives more or fewer alarmist projections of social-economic problems, that it could engender. Technological solutions to address the issue of aging are now a necessity. Systems based on these solutions combine wearable and ambient sensors, processing software, and user interfaces. Their objective is to monitor dependent and frail elderly people in institutions and/or home. The healthcare monitoring for elderly people is a growing application axis thanks to the massive technology development. Family Heroes is a new concept of an automatic healthcare monitoring system based on the Internet of things. In this paper, we will present the global architecture of our system and the preliminary results of the fall detection using only the Kinect V2. The results show the system, in the first stage of validation, detect 70% of falls using a novel approach threshold-based on the variation of angels of the upper body during the movement cycle.