Survey and evaluation of real-time fall detection approaches

  • Authors:
  • James T. Perry;Scott Kellog;Sundar M. Vaidya;Jong-Hoon Youn;Hesham Ali;Hamid Sharif

  • Affiliations:
  • Dept. of Computer Science., Univ. of Nebraska-Omaha, Omaha, NE;Dept. of Computer Science., Univ. of Nebraska-Omaha, Omaha, NE;Dept. of Computer Science., Univ. of Nebraska-Omaha, Omaha, NE;Dept. of Computer Science., Univ. of Nebraska-Omaha, Omaha, NE;Dept. of Computer Science., Univ. of Nebraska-Omaha, Omaha, NE;Dept. of Computer Electronics & Engineering, Univ. of Nebraska-Lincoln, Lincoln, Nebraska

  • Venue:
  • HONET'09 Proceedings of the 6th international conference on High capacity optical networks and enabling technologies
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

As we grow old, our desire for independence does not diminish; yet our health increasingly needs to be monitored. Injuries such as falling can be a serious problem for the elderly. If a person falls and is not able to get assistance within an hour, casualties arising from that fall can result in fatalities as early as 6 months later [1]. It would seem then that a choice between safety and independence must be made. Fortunately, as health care technology advances, simple devices can be made to detect or even predict falls in the elderly, which could easily save lives without too much intrusion on their independence. Much research has been done on the topic of fall detection and fall prediction. Some have attempted to detect falls using a variety of sensors such as: cameras, accelerometers, gyroscopes, microphones, or a combination of the like. This paper is aimed at reporting which existing methods have been found effective by others, as well as documenting the findings of our own experiments. The combination of which will assist in the progression towards a safe, unobtrusive monitoring system for independent seniors.