Automatic system for monitoring independent person requiring occasional assistance

• US 20020171551A1
• Filed: 03/15/2001
• Published: 11/21/2002
• Est. Priority Date: 03/15/2001
• Status: Active Grant

• Current Assignee: Lifeline Systems Company (Koninklijke Philips N.V.)
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Gutta, Srinivas, Pelletier, Daniel, Eshelman, Larry J., Strubbe, Hugo J., Milanski, John
• Granted Patent: US 6,611,206 B2
• Time in Patent Office: Days
• US Class Current: 340/573.1
• CPC Class Codes: A61B 5/0013 Medical image data A61B1/00011, A61B6/56, A61B8/56 take precedence
• CPC Class Codes: A61B 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/14532 for measuring glucose, e.g. by tissue impedance measurement
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G08B 21/0423 detecting deviation from an expected pattern of behaviour or schedule
• CPC Class Codes: G08B 21/0453 worn on the body to detect health condition by physiological monitoring, e.g. electrocardiogram, temperature, breathing detecting, measuring or recording for diagnostic purposes A61B5/00
• CPC Class Codes: G08B 21/0476 Cameras to detect unsafe condition, e.g. video cameras
• CPC Class Codes: G10L 25/66 for extracting parameters related to health condition detecting or measuring for diagnostic purposes A61B5/00
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: Y10S 128/92 Computer assisted medical diagnostics

Abstract

Briefly, an alarm system monitors conditions of an independent person, yet one requiring some supervision, such as an elderly person living alone at home. The system monitors a variety of independent signals and combines them to recognize subtle cues that may indicate there will be a need for intervention by a supervisor.

Claims

1. A device for monitoring a first person, in a zone, who may intermittently require supervision, comprising:

a controller programmed to receive at least one monitor signal from an environment monitor located in a monitored zone;

said monitor signal including at least one of a image data, a video signal, and an audio signal;

said controller being programmed to respond to at least one of a physical pathology and a mental state detectable in said monitor signal and to generate an alarm signal responsively thereto.

2. A device as in claim 1, wherein said controller is programmed to implement a network model responsive to produce respective outputs for multiple physical pathologies.

3. A device as in claim 1, wherein said at least one monitor signal includes an image of a face of said first person.

4. A device as in claim 1, wherein said at least one monitor signal includes an audio signal representing speech, said controller being programmed to detect word patterns in said speech, said alarm signal being responsive to said word patterns.

5. A device as in claim 1, wherein said controller is programmed to distinguish between a normal voice of said person and an abnormal voice of said speaker and to generate said alarm signal responsively thereto.

6. A device as in claim 1, wherein said alarm signal includes at least a portion of said monitor signal immediately prior to and immediately after an incidence of said alarm condition.

7. A device as in claim 1 wherein said alarm signal includes at least one of an audio signal, text data signal, and a video signal.

8. A device as in claim 1, wherein said zone is a living space of said person.

9. A method of monitoring a person requiring occasional supervision, comprising the steps of:

programming a network model to classify at least one of a mental state and a health status of said person responsively to at least one of a video, image, or audio signal;

using said network model to generate a first signal indicative of said at least one of a mental state and a health status to generate a class signal;

combining said class signal with other class data and determining an alarm condition responsively thereto;

transmitting a signal responsive to said class signal to a remote supervisor responsively to a result of said step of determining.

10. A method as in claim 9, further comprising outputting a signal to elicit a behavior from said person to produce said other class data.

11. A method of monitoring an individual in a residence, comprising the steps of:

receiving a video signal;

determining a pattern of movement of said person in said residence responsively to said video signal over a period of time;

detecting an abnormality in said pattern of movement responsively to a result of said step of determining;

generating an alarm signal responsively to a result of said step of detecting.

14. A method as in claim 13, further comprising the step of generating an alarm signal responsively to said step of detecting.

15. A method as in claim 13, wherein said step of detecting a first event includes capturing an image and processing said image, said first signal being responsive to a result of said step of processing.

12. A method of monitoring a person living alone, comprising the steps of:

detecting first and second signals;

filtering each of said first and second signals through a respective classifier to detect an event;

generating an alarm responsively to a result of said step of filtering.

13. A method of monitoring a person, comprising the steps of:

detecting first and second events occurring in said person'"'"'s environment and responsive to said user'"'"'s state or behavior to generate first and second signals, respectively;

said first and second events being distinct in a way other than by the time of incidence;

filtering said first and second signals through a network classifier;

detecting an event responsively to said step of filtering.

16. A method of monitoring an unsupervised person living at home, comprising the steps of:

classifying image data to detect one of a mental state and a health status;

classifying audio data to further detect said one of a mental state and a health status;

classifying an alarm state responsive to both said first step of classifying and said second step of classifying; and

generating an alarm signal responsive to said third step of classifying.