Fall Detection from Human Shape and Motion History Using Video Surveillance

Nowadays, Western countries have to face the growing population of seniors. New technologies can help people stay at home by providing a secure environment and improving their quality of life. The use of computer vision systems offers a new promising solution to analyze people behavior and detect some unusual events. In this paper, we propose a new method to detect falls, which are one of the greatest risk for seniors living alone. Our approach is based on a combination of motion history and human shape variation. Our algorithm provides promising results on video sequences of daily activities and simulated falls.

1. Introduction

Canada, as others Western countries, faces the growing population of seniors. The statistics provided by the Public Health Agency of Canada [2] give us an idea of the problem: in 2001, one Canadian out of eight was older than 65 years old. In 2026, this proportion will be one out of five. It is important to notice that a majority of seniors, 93%, reside in private house, and among them, 29% live alone [2]. One of the greatest danger for old people living alone are the falls. Almost 62% of injury-related hospitalizations for seniors are the result of falls [3]. And the gravity of the situation can increase if the person can not call for help.