Human stability assessment and fall detection based on dynamic descriptors

Abstract

AbstractFall detection systems use a number of different technologies to achieve their goals. This way, they contribute to better life conditions for the elderly community. The artificial vision is one of these technologies and, within this field, it has gained momentum over the course of the last few years as a consequence of the incorporation of different artificial neural networks (ANN's). These ANN's share a common characteristic, they are used to extract descriptors from images and video clips that, properly processed, will determine whether a fall has taken place.These descriptors, which capture kinematic features associated with the fall, are inferred from datasets recorded by young volunteers or actors who simulate falls. Systems based on this concept offer excellent performances in tests which use that kind of datasets. However, given the well‐documented differences between these falls and the real ones, concerns about system performances when processing falls of elderly people are raised.This work implements an alternative approach to the classical use of kinematic descriptors. To do it, for the first time to the best of the authors’ knowledge, the authors propose the introduction of human dynamic stability descriptors used in other fields to determine whether a fall has taken place. These descriptors approach the human body in terms of balance and stability; this way, differences between real and simulated falls become irrelevant, as all falls are a direct result of fails in the continuous effort of the body to keep balance, regardless of other considerations. The descriptors are determined by using the information provided by a neural network able to estimate the body centre of mass and the feet projections onto the ground plane, as well as the feet contact status.The theory behind this new approach and its validity is studied in this article with very promising results, as it is able to match or over exceed the performances of previous systems using kinematic descriptors employing available data and, given the independence of this approach from the conditions of the fall, it has the potential to have a better behaviour than classic systems when facing falls of elderly people.