The paper proposes new technologies to support independence and engagement in elderly people living alone at home in the framework of a new UE Integrated Project. Aim of the study is the development of a light technological infrastructure to be integrated in the homes of old people at reduced costs, allowing the detection of critical health situations. In particular a reliable fall detector is presented, with focus on the protection and assistance to the elderly in the home environment. The integrated fall detector prototype includes two different sensors: a 3D Time-of-Flight range camera and a wearable MEMS accelerometer. The devices are connected in a networked configuration with custom interface circuits to a central PC that collects and processes the information with a multi-threading approach. For each sensor, an optimized algorithm for fall-detection has been developed and benchmarked on a collected multimodal database. This work is expected to lead to a multi-sensory approach employing appropriate fusion techniques aiming to improve system efficiency and reliability.
A Networked Multisensor System for Ambient Assisted Living application
Malfatti, Mattia;Gonzo, Lorenzo;
2009-01-01
Abstract
The paper proposes new technologies to support independence and engagement in elderly people living alone at home in the framework of a new UE Integrated Project. Aim of the study is the development of a light technological infrastructure to be integrated in the homes of old people at reduced costs, allowing the detection of critical health situations. In particular a reliable fall detector is presented, with focus on the protection and assistance to the elderly in the home environment. The integrated fall detector prototype includes two different sensors: a 3D Time-of-Flight range camera and a wearable MEMS accelerometer. The devices are connected in a networked configuration with custom interface circuits to a central PC that collects and processes the information with a multi-threading approach. For each sensor, an optimized algorithm for fall-detection has been developed and benchmarked on a collected multimodal database. This work is expected to lead to a multi-sensory approach employing appropriate fusion techniques aiming to improve system efficiency and reliability.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.