Image processing sensor systems

• US 9,740,921 B2
• Filed: 03/07/2016
• Issued: 08/22/2017
• Est. Priority Date: 02/26/2009
• Status: Active Grant

• Current Assignee: Tko Enterprises, Inc.
• Original Assignee: Tko Enterprises, Inc.
• Inventors: McClure, Neil L., Wieland, Ralph David
• Primary Examiner(s): Aghevli, Reza
• Application Number:
  US15/063,402
• Publication Number:
  US 20160188965A1
• Time in Patent Office: 533 Days
• Field of Search: None
• CPC Class Codes: A01M 31/002 Detecting animals in a given area
• CPC Class Codes: A61B 5/1116 Determining posture transitions
• CPC Class Codes: A61B 5/1117 Fall detection
• CPC Class Codes: G06F 18/2413 based on distances to training or reference patterns
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• 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 13/1961 Movement detection not involving frame subtraction, e.g. motion detection on the basis of luminance changes in the image
• CPC Class Codes: G08B 13/19663 Surveillance related processing done local to the camera
• 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

Abstract

An image processing sensor system functions as a standalone unit to capture images and process the resulting signals to detect objects or events of interest. The processing significantly improves selectivity and specificity of detection objects and events in a series of motions that may precede a patient who is at elevated risk of falling.

Claims

1. A method of image processing, comprising the steps of:

constructing a results key at a first processing station by use of image processing algorithms operating upon a plurality of images representative of different human individuals to produce the results key as a data set that contains sufficient information to identify a human being as an object of interest with a statistical level of certainty accommodating various shapes and sizes of human beings;

making the results key available to a central computer system that includes at least one image capture and processing device remote from the first processing station, where the image capture and processing device is operable to capture an image presented to a field of view of the image capture and processing device; and

using the results key at a central computer system located remotely from the first processing station to process the field of view image to identify a human being as the object of interest, and to provide an output signal indicating that the human being is present according to parameters established by the results key at a level of analysis indicative of human beings inclusive of various shapes and sizes of human beings.

2. The method of claim 1, wherein the step of making the results key available is performed by using a portable memory component to transfer the results key from the first processing station to the central computer system.

3. The method of claim 1, wherein the step of making the results key available is performed by using a wireless transmission to transfer the results key from the first processing station to the central computer system.

4. The system of claim 1, wherein the step of making the results key available is performed by using a cable interconnect to transfer the results key from the first processing station to the central computer system.

5. The method of claim 1, wherein the step of constructing the results key includes using data from one or more physical property sensors to enhance the level of statistical certainty.

6. The method of claim 5, wherein the image capture and processing device further includes one or more physical property sensors configured to provide property sensor output, and the step of using the results key includes use of the physical property sensor output to facilitate processing of the field of view image.

7. The method of claim 1, wherein the image capture and processing device further includes a real time clock configured to provide a time output signal, and the step of using the results key includes use of the time function output signal to facilitate processing of the field of view image.

8. The method of claim 1, wherein step of using the results key includes providing the output control signal based upon observed interaction over time between a plurality of discrete objects of interests.

9. The method of claim 1, wherein step of using the results key includes changing a sampling rate of the field of view image based upon a detected event.

10. The method of claim 1, wherein the step of providing the results key includes updating the results key with an improved results key, where the improved results key provides a higher degree of statistical certainty for identification of the object of interest.

14. The method of claim 1 further comprising a step of performing an analysis of specific human movement occurring in the field of view.

15. The method of claim 14, wherein the step of performing the analysis includes an analysis to ascertain movement consistent with a human getting out of bed.

19. The method of claim 1, wherein the step of using the results key includes passive imaging of the field of view.

11. In an image capture and processing device that detects human movements, the improvement comprising:

a processor configured to operate upon image data to ascertain human movements by application of a results key as a data set that contains sufficient information to identify in the image data set a human being as an object of interest with a statistical level of certainty accommodating various shapes and sizes of human beings;

means for analyzing the human movements to ascertain specific movements related to at least one action selected from the group consisting of characteristic movement patterns that are defined by parameters provided by the results key; and

means for providing an output signal when the specific movements occur in the field of view.

12. The image capture and processing device of claim 11, further including a remotely monitored data display unit configured to display an alarm upon receipt of the output signal.

13. The image capture and processing device of claim 11, wherein the means for analyzing includes an artificially intelligent algorithm that is trained to detect the specific human movement.

16. An image capture and processing device, comprising:

an imager configured to capture image data representative of an image presented to a field of view of the image capture and processing device, and

a computer system with data storage that contains a results key as a data set that contains sufficient information to identify a human being as an object of interest with a statistical level of certainty accommodating various shapes and sizes of human beings,

the computer system being configured to receive the image data from the imager and to process the same by applying parameters established by the results key to identify a human being as the object of interest, and to provide an output signal indicating that the human being is present according to parameters established by the results key at a level of analysis indicative of human beings inclusive of various shapes and sizes of human beings.

17. The image capture and processing device of claim 16, wherein the computer system is configured to provide an analysis of specific human movement occurring in the field of view.

18. The image capture and processing device of claim 17, wherein the analysis includes an analysis to ascertain movement consistent with a human getting out of bed.