A Smart Sensor to Detect the Falls of the Elderly.

Presentation on theme: "A Smart Sensor to Detect the Falls of the Elderly."— Presentation transcript:

1 A Smart Sensor to Detect the Falls of the Elderly

2 2 introduction  Falls are a major health hazard for the elderly and a major obstacle to independent living  The estimated incidence of falls for both institutionalized and independent persons aged over 75 is at least 30 percent per year

3 3 introduction  The SIMBAD( Smart Inactivity Monitor using Array-Based Detectors) system ultimately aims to enhance the quality of life of the elderly, afford them a greater sense of security,and facilitate independent living

4 4 Justification for their approach  the current and emerging technologies have key limitations:  Simple sensors, such as single- or dual- element PIR (passive infrared) sensors, provide fairly crude data that’s difficult to interpret  Wearable devices such as wrist communicators and motion detectors have potential but rely on a person’s ability and willingness to wear them

5 5 Justification for their approach  Cameras might appear intrusive and require considerable human resources to monitor activity.  Machine interpretation of camera images is complex and might be difficult in this application area

6 6 Justification for their approach  IRISYS (InfraRed Integrated Systems) thermal imaging sensors can help overcome these limitations.  The sensor is wall mounted, and users don’t have to wear a device  this solution’s cost-effectiveness, because the low-level data lacks detail, the system will seem less intrusive to users.

7 7 Justification for their approach

8 8 SIMBAD’ s technical development  The IRISYS sensor can reliably locate and track a thermal target in the sensor’s field of view, providing size, location, and velocity information.

9 9 SIMBAD’ s technical development  SIMBAD considers two distinct characteristics of observed behavior:  First, it analyzes target motion to detect falls’ characteristic dynamics  Second, it monitors target inactivity and compares it with a map of acceptable periods of inactivity in different locations in the field of view.

10 10 SIMBAD’ s technical development  the prototype system architecture, which has five major components  Tracker  The tracker identifies and tracks an elliptical target using data from the IRISYS sensor  The tracker provides real-time estimates of target position, velocity, shape, and size.

11 11 SIMBAD’ s technical development  Fall detector  This subsystem employs a neural network to classify falls using vertical-velocity estimates derived either directly from IRISYS sensor data or from the tracker  Subtle-motion detector  This relatively simple signal-based mechanism identifies small movements in the sensor’s field of view

12 12 SIMBAD’ s technical development  Because such movements generate insufficient responses to activate the tracker  Inactivity monitor  This uses output from the tracker and subtle- motion detector to monitor periods of inactivity in the sensor’s field of view  Once a target is no longer visible, this subsystem monitors two distinct types of inactivity in the neighborhood of the last known position

13 13 SIMBAD’ s technical development  Coarse-scale inactivity identifies the period of time since the tracker last tracked the object.  Fine-scale inactivity identifies the period of time since the system detected subtle motion in some neighborhood of the object’s last known position.

14 14 SIMBAD’ s technical development  High-level reasoner  This subsystem performs the reasoning required to monitor the output of the fall detector, inactivity monitor, and subtle-motion detector and to generate alarm signals if required.  The system generates two classes of alarm— those triggered by excessive periods of inactivity (according to the risk map) and those triggered by the detection of a fall.

15 15 SIMBAD’ s technical development

16 16 conclusion  To refine SIMBAD and extend its capabilities, they’re  Improving the fall detection algorithms, which, might involve developing a more elaborate representation of a fall’s dynamics  Creating algorithms to track, locate, multiple individuals in a multiroom environment

17 17 conclusion  Developing a sensor subsystem that lets a group of sensors monitor the activity of one or more individuals throughout a building’s living spaces and discriminate between real and false alerts  Integrating the sensor in a host telecare system  Conducting further field trials to assess SIMBAD’s usefulness in supporting the elderly living in the community