Computer vision based elderly care monitoring system

• US 20030058111A1
• Filed: 07/03/2002
• Published: 03/27/2003
• Est. Priority Date: 09/27/2001
• Status: Abandoned Application

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Lin, Yun-Ting, Brodsky, Tomas, Trajkovic, Miroslav, Lee, Mi-Suen, Gutta, Srinivas, Philomin, Vasanth, Cohen-Solal, Eric, Strubbe, Hugo, Dagtas, Serhan
• Application Number:
  US10/189,272
• Publication Number:
  US 20030058111A1
• Time in Patent Office: Days
• US Class Current: 340/573.1
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/292 Multi-camera tracking
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training
• CPC Class Codes: G08B 13/19602 Image analysis to detect motion of the intruder, e.g. by frame subtraction
• CPC Class Codes: G08B 13/19608 Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position
• CPC Class Codes: G08B 13/19613 Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
• CPC Class Codes: G08B 13/19641 Multiple cameras having overlapping views on a single scene
• CPC Class Codes: G08B 21/0423 detecting deviation from an expected pattern of behaviour or schedule
• CPC Class Codes: G08B 21/043 detecting an emergency event, e.g. a fall
• CPC Class Codes: G08B 21/0476 Cameras to detect unsafe condition, e.g. video cameras
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

A method for monitoring a person of interest in a scene, the method comprising: capturing image data of the scene; detecting and tracking the person of interest in the image data; analyzing features of the person of interest; and detecting at least one of an event and behavior associated with the detected person of interest based on the features; and informing a third party of the at least one detected events and behavior.

Claims

1. A method for monitoring a person of interest in a scene, the method comprising:

capturing image data of the scene;

detecting and tracking the person of interest in the image data;

analyzing features of the person of interest; and

detecting at least one of an event and behavior associated with the detected person of interest based on the features; and

informing a third party of the at least one detected event and behavior.

2. The method of claim 1, wherein the person of interest is selected from a group comprising an elderly person, a physically handicapped person, and a mentally challenged person.

3. The method of claim 2, wherein the detecting of at least one of an event and behavior detects at least one of an abnormal event and abnormal behavior.

4. The method of claim 2, wherein the scene is a residence of the person of interest.

5. The method of claim 1, wherein the detecting and tracking comprises segmenting the image data into at least one moving object and background objects, the at least one moving object being the person of interest.

6. The method of claim 5, wherein the detecting and tracking further comprises:

learning and recognizing a human shape; and

detecting a feature of the moving object indicative of a person.

7. The method of claim 6, wherein the detecting of a feature of the moving object indicative of a person comprises detecting a face on the moving object.

8. The method of claim 3, wherein the detecting of abnormal events comprises:

comparing the analyzed features with predetermined criteria indicative of a specific event; and

determining whether the specific event has occurred based on the comparison.

9. The method of claim 8, wherein the specific event is selected from a group comprising a fall-down, stagger, and panic gesturing.

10. The method of claim 8, wherein the analyzing comprises analyzing one or more of a temporal sequence of the person of interest, a motion characteristics of the person of interest, and a trajectory of the person of interest.

11. The method of claim 8, wherein the determining step comprises assigning a factor indicative of how well each of the analyzed features comply with the predetermined criteria indicative of the specific event and applying a arithmetic expression to the factors to determine a likelihood that the specific event has occurred.

12. The method of claim 3, wherein the detecting of abnormal events comprises modeling a plurality of sample abnormal events and comparing each of the plurality of sample abnormal events to a sequence of the image data.

13. The method of claim 3, wherein the detecting of abnormal behavior comprises:

computing a level of body motion of the person of interest based on the detected tracking of the person of interest;

computing a probability density for modeling the person of interest'"'"'s behavior;

developing a knowledge-based description of predetermined normal behaviors and recognizing them from the probability density; and

detecting the absence of the normal behaviors.

14. The method of claim 3, wherein the informing comprises sending a message to the third party that at least one of the abnormal event and abnormal behavior has occurred.

15. The method of claim 14, wherein the sending comprises generating an alarm signal and transmitting the alarm signal to a central monitoring station.

16. The method of claim 14, wherein the sending comprises transmitting at least a portion of the captured image data to the third person.

17. A system for monitoring a person of interest in a scene, the system comprising:

at least one camera for capturing image data of the scene;

a processor operatively connected for input of the image data for; and

detecting and tracking the person of interest in the image data;

analyzing features of the person of interest;

detecting at least one of an event and behavior associated with the detected person of interest based on the features; and

informing a third party of the at least one detected event and behavior.

18. A computer program product embodied in a computer-readable medium for monitoring a person of interest in a scene, the computer program product comprising:

computer readable program code means for capturing image data of the scene;

computer readable program code means for detecting and tracking the person of interest in the image data;

computer readable program code means for analyzing features of the person of interest; and

computer readable program code means for detecting at least one of an event and behavior associated with the detected person of interest based on the features; and

computer readable program code means for informing a third party of the at least one detected event and behavior.

19. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for monitoring a person of interest in a scene, the method comprising:

capturing image data of the scene;

detecting and tracking the person of interest in the image data;

analyzing features of the person of interest; and

detecting at least one of an event and behavior associated with the detected person of interest based on the features; and

informing a third party of the at least one detected event and behavior.