Journal of Harmonized Research in Engineering

MOTION HISTORY IMAGE BASED HUMAN FALL DETECTION

Abstract

Author(s): Pooja Shukla*, Arti Tiwari

Day by the count of elderly people living alone at home increases. Fall is one of the major risks for elderly people. Sometimes older people may get serious injury to their backbone (spinal cord) and that may lead to death. Sometimes fallen injured elderly may be lying on the ground for several hours after a fall incident has occurred. This makes it important to have a fall detection system. In this paper, we propose a MHI based fall detection system. Our approach is based on angle of falling. Our algorithm provides promising results on video sequences of daily activities and simulated falls.