Abstract
Fall detection is one of the most investigated themes in the research on assistive solutions for aged people. In particular, a false-alarm-free discrimination between falls and non-falls is indispensable, especially to assist elderly people living alone. Current technological solutions designed to monitor several types of activities in indoor environments can guarantee absolute privacy to the people that decide to rely on them. Devices integrating RGB and depth cameras, such as the Microsoft Kinect, can ensure privacy and anonymity, since the depth information is considered to extract only meaningful information from video streams. In this paper, we propose an accurate fall detection method investigating the depth frames of the human body using a single device in a top-view configuration, with the subjects located under the device inside a room. Features extracted from depth frames train a classifier based on a binary support vector machine learning algorithm. The dataset includes 32 falls and 8 activities considered for comparison, for a total of 800 sequences performed by 20 adults. The system showed an accuracy of 98.6% and only one false positive.
Highlights
In contemporary society, the aging of the population is a growing phenomenon that requires investments [1] for the development of assisted living environments which are able to provide technological tools to support active aging in nursing homes or in health care facilities
We propose an accurate fall detection method investigating the depth frames of the human body using a single device in a top-view configuration, with the subjects located under the device inside a room
The method developed in the proposed work consisted of three main blocks: real-time acquisition of the height of the maximum point associated to the person and extraction of the blob area of the person from the depth frame; features extraction starting from the depth data; features processing and support vector machine (SVM) models definition
Summary
The aging of the population is a growing phenomenon that requires investments [1] for the development of assisted living environments which are able to provide technological tools to support active aging in nursing homes or in health care facilities. Among the Ambient Assisted Living (AAL) research and development issues, the availability of automatic fall detection solutions could reduce the risk of complications deriving from a critical event [2]. The aim of this work is to design an automatic system for fall detection based on the depth data extracted from the Kinect sensor. The choice of this technology was motivated by the possibility of realizing an unobtrusive monitoring of the environment of interest, guaranteeing respect for user privacy. By evaluating the use of several currently available technologies, it is possible to consider the following issues and typologies:
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
