Determining a confidence for a motion zone identified as a location of motion for motion detected by wireless signals

• US 10,460,581 B1
• Filed: 05/15/2019
• Issued: 10/29/2019
• Est. Priority Date: 05/15/2019
• Status: Active Grant

• Current Assignee: Cognitive Systems Corp.
• Original Assignee: Cognitive Systems Corp.
• Inventors: Devison, Stephen Arnold, Omer, Mohammad
• Primary Examiner(s): McNally, Kerri L
• Application Number:
  US16/413,165
• Time in Patent Office: 167 Days
• Field of Search: 3405453
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G08B 13/19 using infrared-radiation detection systems G08B13/194 takes precedence
• CPC Class Codes: G08B 13/19606 Discriminating between target movement or movement in an area of interest and other non-signicative movements, e.g. target movements induced by camera shake or movements of pets, falling leaves, rotating fan
• CPC Class Codes: G08B 13/2491 Intrusion detection systems, i.e. where the body of an intruder causes the interference with the electromagnetic field
• CPC Class Codes: G08B 29/185 Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system

Abstract

In a general aspect, a method is presented for determining a motion-zone confidence. In some aspects, the method includes obtaining, from a database of a motion detection system, ranges of motion-zone parameters associated with respective motion zones in a space between wireless communication devices. The method also includes analyzing the ranges of motion-zone parameters to identify, for one or more of the motion zones, overlapping ranges of motion-zone parameters and non-overlapping parameter ranges of motion-zone parameters. The method additionally includes storing, in the database of the motion detection system, the overlapping and non-overlapping ranges of motion-zone parameters. The overlapping and non-overlapping ranges of motion-zone parameters are used to identify one of the motion zones based on a motion event detected by the motion detection system.

Claims

1. A method comprising:

obtaining, from a database of a motion detection system, ranges of motion-zone parameters associated with respective motion zones in a space between wireless communication devices, the ranges of motion-zone parameters derived from sets of channel response data based on wireless signals communicated over wireless links through the space;

analyzing the ranges of motion-zone parameters to identify, for one or more of the motion zones, overlapping ranges of motion-zone parameters and non-overlapping parameter ranges of motion-zone parameters;

storing, in the database of the motion detection system, the overlapping and non-overlapping ranges of motion-zone parameters; and

using the overlapping and non-overlapping ranges of motion-zone parameters to identify one of the motion zones based on a motion event detected by the motion detection system.

2. The method of claim 1, comprising:

generating motion-zone parameters for the motion event based on one or more time series of statistical parameters produced in response to the motion event; and

determining a confidence level, based on the motion-zone parameters, that characterizes a degree to which the identified motion zone represents a location of the motion event.

3. The method of claim 2, wherein determining the confidence level comprises:

determining a statistical boundary between first values of motion-zone parameters associated with the identified motion zone and second values of motion-zone parameters associated with a second motion zone, the statistical boundary representing an equal confidence level of the motion event occurring in either the identified motion zone or the second motion zone; and

determining a distance of the motion-zone parameters from the statistical boundary towards the first values;

wherein the distance, when increasing towards the first values, corresponds to an increasing confidence level that the identified motion zone represents the location of the motion event.

4. The method of claim 3, wherein determining the statistical boundary comprises using a support vector machine to determine a hyperplane between the first values and the second values.

5. The method of claim 1, wherein the method comprises:

repeating the operations, over multiple iterations for respective time frames, of obtaining ranges of motion-zone parameters, analyzing the ranges of motion-zone parameters, storing the overlapping and non-overlapping ranges of motion-zone parameters, and using the overlapping and non-overlapping ranges of motion-zone parameters;

determining a difference by comparing, from a subsequent time frame, subsequent overlapping and non-overlapping ranges of motion-zone parameters with prior overlapping and non-overlapping ranges of motion-zone parameters from a prior time frame; and

updating, in the database of the motion detection system, one or both of the overlapping and non-overlapping ranges of motion-zone parameters based on the difference.

6. The method of claim 1, comprising:

generating sets of motion-zone parameters characterizing respective motion zones, each set of motion-zone parameters generated from portions of a time series of statistical parameters bounded by respective time intervals, each time series of statistical parameters based on a respective set of channel response data.

7. The method of claim 6, comprising:

determining, by analyzing multiple time windows within each of the time intervals, ranges of motion-zone parameters associated with each respective motion zone.

8. A system comprising:

wireless communication devices in a wireless communication network that are configured to exchange wireless signals over wireless links, each wireless link defined between a respective pair of the wireless communication devices; and

one or more processors; and

memory storing instructions that are configured to perform operations when executed by the one or more processors, the operations comprising;

obtaining, from a database of a motion detection system, ranges of motion-zone parameters associated with respective motion zones in a space between wireless communication devices, the ranges of motion-zone parameters derived from sets of channel response data based on wireless signals communicated over wireless links through the space;

analyzing the ranges of motion-zone parameters to identify, for one or more of the motion zones, overlapping ranges of motion-zone parameters and non-overlapping parameter ranges of motion-zone parameters;

storing, in the database of the motion detection system, the overlapping and non-overlapping ranges of motion-zone parameters; and

using the overlapping and non-overlapping ranges of motion-zone parameters to identify one of the motion zones based on a motion event detected by the motion detection system.

9. The system of claim 8, the operations comprising:

generating motion-zone parameters for the motion event based on one or more time series of statistical parameters produced in response to the motion event; and

determining a confidence level, based on the motion-zone parameters, that characterizes a degree to which the identified motion zone represents a location of the motion event.

10. The system of claim 9, wherein determining the confidence level comprises:

determining a statistical boundary between first values of motion-zone parameters associated with the identified motion zone and second values of motion-zone parameters associated with a second motion zone, the statistical boundary representing an equal confidence level of the motion event occurring in either the identified motion zone or the second motion zone; and

determining a distance of the motion-zone parameters from the statistical boundary towards the first values;

wherein the distance, when increasing towards the first values, corresponds to an increasing confidence level that the identified motion zone represents the location of the motion event.

11. The system of claim 10, wherein determining the statistical boundary comprises using a support vector machine to determine a hyperplane between the first values and the second values.

12. The system of claim 8, wherein the operations comprise:

repeating the operations, over multiple iterations for respective time frames, of obtaining ranges of motion-zone parameters, analyzing the ranges of motion-zone parameters, storing the overlapping and non-overlapping ranges of motion-zone parameters, and using the overlapping and non-overlapping ranges of motion-zone parameters;

determining a difference by comparing, from a subsequent time frame, subsequent overlapping and non-overlapping ranges of motion-zone parameters with prior overlapping and non-overlapping ranges of motion-zone parameters from a prior time frame; and

updating, in the database of the motion detection system, one or both of the overlapping and non-overlapping ranges of motion-zone parameters based on the difference.

13. The system of claim 8, the operations comprising:

generating sets of motion-zone parameters characterizing respective motion zones, each set of motion-zone parameters generated from portions of a time series of statistical parameters bounded by respective time intervals, each time series of statistical parameters based on a respective set of channel response data.

14. The system of claim 13, the operations comprising:

determining, by analyzing multiple time windows within each of the time intervals, ranges of motion-zone parameters associated with each respective motion zone.

15. A non-transitory computer-readable medium storing instructions that, when executed by data processing apparatus, cause the data processing apparatus to perform operations comprising:

obtaining, from a database of a motion detection system, ranges of motion-zone parameters associated with respective motion zones in a space between wireless communication devices, the ranges of motion-zone parameters derived from sets of channel response data based on wireless signals communicated over wireless links through the space;

analyzing the ranges of motion-zone parameters to identify, for one or more of the motion zones, overlapping ranges of motion-zone parameters and non-overlapping parameter ranges of motion-zone parameters;

storing, in the database of the motion detection system, the overlapping and non-overlapping ranges of motion-zone parameters; and

using the overlapping and non-overlapping ranges of motion-zone parameters to identify one of the motion zones based on a motion event detected by the motion detection system.

16. The computer-readable medium of claim 15, the operations comprising:

generating motion-zone parameters for the motion event based on one or more time series of statistical parameters produced in response to the motion event; and

determining a confidence level, based on the motion-zone parameters, that characterizes a degree to which the identified motion zone represents a location of the motion event.

17. The computer-readable medium of claim 16, wherein determining the confidence level comprises:

determining a statistical boundary between first values of motion-zone parameters associated with the identified motion zone and second values of motion-zone parameters associated with a second motion zone, the statistical boundary representing an equal confidence level of the motion event occurring in either the identified motion zone or the second motion zone; and

determining a distance of the motion-zone parameters from the statistical boundary towards the first values;

wherein the distance, when increasing towards the first values, corresponds to an increasing confidence level that the identified motion zone represents the location of the motion event.

18. The computer-readable medium of claim 17, wherein determining the statistical boundary comprises using a support vector machine to determine a hyperplane between the first values and the second values.

19. The computer-readable medium of claim 15, wherein the operations comprises:

repeating the operations, over multiple iterations for respective time frames, of obtaining ranges of motion-zone parameters, analyzing the ranges of motion-zone parameters, storing the overlapping and non-overlapping ranges of motion-zone parameters, and using the overlapping and non-overlapping ranges of motion-zone parameters;

determining a difference by comparing, from a subsequent time frame, subsequent overlapping and non-overlapping ranges of motion-zone parameters with prior overlapping and non-overlapping ranges of motion-zone parameters from a prior time frame; and

updating, in the database of the motion detection system, one or both of the overlapping and non-overlapping ranges of motion-zone parameters based on the difference.

20. The computer-readable medium of claim 15, the operations comprising:

generating sets of motion-zone parameters characterizing respective motion zones, each set of motion-zone parameters generated from portions of a time series of statistical parameters bounded by respective time intervals, each time series of statistical parameters based on a respective set of channel response data.

21. The computer-readable medium of claim 20, the operations comprising:

determining, by analyzing multiple time windows within each of the time intervals, ranges of motion-zone parameters associated with each respective motion zone.