Combination of Motion History Image and Approximated Ellipse Method for Human Fall Detection System

Elvira Sukma Wahyuni and Mohd Brado Frasetyo (Universitas Islam Indonesia, Indonesia); Hendra Setiawan (Electrical Engineering Universitas Islam Indonesia Yogyakarta, Indonesia)

Indonesia has a high number of elderly people, who live alone without any family at home. This matter has a high risk for elderly in biological aspect, in case something goes wrong like fall, therefore a fall detection systems is needed for monitoring elderly conditions at home. This paper propose a human fall detection system using combination of Motion History Image(MHI) and Approximated Ellipse. These method works by generating that represents object motion and and that represents object movement direction. The result showed, this research obtain a good performance in fall detection from amoving object with accuracy is 83.33%

Journal: International Journal of Simulation: Systems, Science and Technology IJSSST V19

Published: Jun 30, 2018

DOI: 10.5013/IJSSST.a.19.03.13