Object intrusion detection system and method

• US 10,789,506 B2
• Filed: 09/24/2018
• Issued: 09/29/2020
• Est. Priority Date: 09/24/2018
• Status: Active Grant

• Current Assignee: Rockwell Automation Technologies Incorporated (Allen-Bradley Co., Inc.)
• Original Assignee: Rockwell Automation Technologies Incorporated (Allen-Bradley Co., Inc.)
• Inventors: Li, Mei, Boutaud, Frederic
• Primary Examiner(s): Patel, Mahendra R
• Application Number:
  US16/139,436
• Publication Number:
  US 20200097755A1
• Time in Patent Office: 736 Days
• Field of Search: 382107, 340345
• CPC Class Codes: G01S 17/04 Systems determining the presence of a target
• CPC Class Codes: G01S 17/894 3D imaging with simultaneous measurement of time-of-flight at a 2D array of receiver pixels, e.g. time-of-flight cameras or flash lidar
• CPC Class Codes: G01S 7/4863 Detector arrays, e.g. charge-transfer gates
• CPC Class Codes: G01S 7/4865 Time delay measurement, e.g. time-of-flight measurement, time of arrival measurement or determining the exact position of a peak peak detection in noise, signal conditioning G01S7/487
• CPC Class Codes: G01S 7/4876 by removing unwanted signals G01S7/495 takes precedence
• CPC Class Codes: G06F 1/3206 Monitoring of events, devices or parameters that trigger a change in power modality
• CPC Class Codes: G06F 16/2237 Vectors, bitmaps or matrices
• 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: G08B 13/184 using radiation reflectors
• CPC Class Codes: G08B 13/19602 Image analysis to detect motion of the intruder, e.g. by frame subtraction
• CPC Class Codes: G08B 29/185 Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system

Abstract

A three-dimensional (3D) sensor device achieves high intrusion detection probability while keeping the probability of a false intrusion detection low by capturing a set of multiple spatial or temporal samples of a measured parameter for an object detected in the sensor'"'"'s field of view. When an object is detected in the field of view, the TOF sensor device defines a window of N pixels comprising a subset of the pixels corresponding to the object, and obtains N distance measurements corresponding to the N pixels of the window. If the number of the N distance values that are less than a defined threshold distance is equal to or greater than a selected threshold value M (an integer less than N), the TOF sensor device determines that the object is intruding within a protective field and generates a suitable output.

Claims

1. A sensor device, comprising:

a distance determination component configured to receive pixel data associated with respective pixels of a field of view, and to identify an object within the field of view corresponding to a first subset of the pixels; and

an intrusion detection component configured to define a pixel window comprising a second subset of the first subset of the pixels, wherein the second subset comprises N pixels, and N is an integer,

wherein

the distance determination component is further configured to determine N distance values corresponding to the N pixels of the pixel window based on a subset of the pixel data corresponding to the second subset of the first subset of the pixels,

the intrusion detection component is further configured to count a number K of the N distance values that are less than a defined distance threshold, and

the sensor device further comprises a control output component configured to, in response to determining that the number K of the N distance values that are less than the defined distance threshold is equal to or greater than a defined threshold value M, generate an output signal configured to at least one of disconnect power from an industrial machine, place an industrial automation system in safe operation mode, or send a notification to one or more client devices.

2. The sensor device of claim 1, wherein

the distance determination component is further configured to

identify a subset of the N distance values that are outside a defined valid distance range, and

replace the subset of the N distance values with replacement distance values to yield a modified set of N distance values;

and

the intrusion detection component is configured to count the number of the N distance values from the modified set of N distance values.

3. The sensor device of claim 2, wherein the distance determination component is configured to generate a replacement distance value, of the replacement distance values, for one of the subset of the N distance values corresponding to one of the pixels based on another subset of the N distance values corresponding to pixels that are adjacent to the one of the pixels.

4. The sensor device of claim 1, wherein

the distance determination component is further configured to:

identify a subset of the N distance values that are outside a defined valid distance range, and

remove the subset of the N distance values to yield a reduced set of distance values; and

the intrusion detection component is configured to;

reduce the defined threshold value M based on a number of the subset of the N distance values removed by the distance determination component to yield a modified threshold value M_MODIFIED,

count a number of the reduced set of distance values that are less than the defined distance threshold, and

generate the output signal in response to determining that the number of the reduced set of distance values that are less than the defined distance threshold is equal to or greater than the modified threshold value M_MODIFIED.

5. The sensor device of claim 1, wherein the intrusion detection component is configured to set the number N of pixels comprising the pixel window based on a number of the first subset of the pixels corresponding to the object.

6. The sensor device of claim 5, wherein the intrusion detection component is further configured to select the threshold value M based on the number N.

7. The sensor device of claim 6, wherein the intrusion detection component is configured to select the threshold value M to achieve a defined minimum intrusion detection probability according to a detection probability algorithm that defines the intrusion detection probability as a function of M and N.

8. The sensor device of claim 1, wherein

the distance determination component is further configured to determine the N distance values at multiple different times within a measuring sequence to yield multiple sets of N distance values, and

the intrusion detection component is configured to,

for each pixel of the pixel window, average a subset of the distance values, from the multiple sets of N distance values, corresponding to the pixel, wherein averaging the subset of the distance values for each pixel yields N averaged distance values,

count the number K of the N averaged distance values that are less than the defined distance threshold, and

generate the output signal in response to determining that the number K of the N averaged distance values is equal to or greater than the defined threshold value M.

20. The sensor device of claim 1, further comprising a user interface component configured to receive user input that defines the defined distance threshold.

9. A method for detecting intrusion of an object within a protective field, comprising:

receiving, by a sensor device comprising a processor, pixel data for respective pixels of a field of view;

identifying, by the sensor device based on analysis of the pixel data, an object within the field of view, wherein the object corresponds to a first subset of the pixels;

defining, by the sensor device, a pixel window comprising a second subset of the first subset of the pixels, wherein the second subset comprises N pixels, and N is an integer;

determining, by the sensor device, N distance values corresponding to the N pixels of the pixel window based on the pixel data;

counting, by the sensor device, a number K of the N distance values that are less than a defined distance threshold; and

in response to determining that the number K of the N distance values that are less than the defined distance threshold is equal to or greater than a defined threshold value M, generating, by the sensor device, an output signal configured to at least one of disconnect power from an industrial machine, place an industrial automation system in safe operation mode, or send a notification to one or more client devices.

10. The method of claim 9, wherein the determining the N distance values comprises:

identifying, based on the pixel data, a subset of the N distance values that are outside a defined valid distance range; and

replacing the subset of the N distance values with replacement distance values to yield a modified set of N distance values.

11. The method of claim 10, wherein the replacing the subset of the N distance values comprises replacing each distance value, of the subset of the N distance values, corresponding to one of the pixels with a replacement value calculated based on another subset of the N distance values corresponding to pixels that are adjacent to the one of the pixels.

12. The method of claim 9, wherein the counting comprises:

identifying a subset of the N distance values that are outside a defined valid distance range, wherein the subset comprises N_OUTLINER distance values, and N_OUTLINER is an integer;

removing the N_OUTLINER distance values from the N distance values to yield a reduced set of distance values;

reducing the defined threshold value M based on a value of N_OUTLINER to yield a modified threshold value M_MODIFIED;

counting a number of the reduced set of distance values that are less than the defined distance threshold; and

generating the output signal in response to determining that the number of the reduced set of distance values that are less than the defined distance threshold is equal to or greater than the modified threshold value M_MODIFIED.

13. The method of claim 9, wherein the defining the pixel window comprises setting the number N of pixels comprising the pixel window based on a number of the first subset of the pixels.

14. The method of claim 13, further comprising setting, by the sensor device, the threshold value M based on the number N of pixels comprising the pixel window.

15. The method of claim 14, wherein the setting the threshold value M comprises selecting the threshold value M to achieve a defined minimum intrusion detection probability according to a detection probability algorithm that defines the intrusion detection probability as a function of M and N.

16. A non-transitory computer-readable medium having stored thereon instructions that, in response to execution, cause a sensor device to perform operations, the operations comprising:

receiving pixel data for respective pixels of a field of view;

identifying an object within the field of view based on analysis of the pixel data, wherein the object corresponds to a first subset of the pixels;

defining a pixel window comprising a second subset of the first subset of the pixels, wherein the second subset comprises N pixels, and N is an integer;

determining N distance values corresponding to the N pixels of the pixel window based on a subset of the pixel data corresponding to the second subset of the first subset of the pixels;

counting a number K of the N distance values that are less than a defined distance threshold; and

in response to determining that the number K of the N distance values that are less than the defined distance threshold is equal to or greater than a defined threshold value M, outputting a signal configured to at least one of disconnect power from an industrial machine, place an industrial automation system in safe operation mode, or send a notification to one or more client devices.

17. The non-transitory computer-readable medium of claim 16, wherein the counting comprises;

identifying a subset of the N distance values that are outside a defined valid distance range, wherein the subset comprises N_OUTLINER distance values, and N_OUTLIER is an integer;

removing the N_OUTLINER distance values from the N distance values to yield a reduced set of distance values;

reducing the defined threshold value M based on a value of N_OUTLINER to yield a modified threshold value M_MODIFIED;

counting, as the number K, a number of the reduced set of distance values that are less than the defined distance threshold; and

generating the signal in response to determining that the number K of the reduced set of distance values that are less than the defined distance threshold is equal to or greater than the modified threshold value M_MODIFIED.

18. The non-transitory computer-readable medium of claim 16, wherein the defining the pixel window comprises setting the number N of pixels comprising the pixel window based on a number of the first subset of the pixels.

19. The non-transitory computer-readable medium of claim 16, wherein the determining the N distance values comprises:

identifying, based on the pixel data, a subset of the N distance values that are outside a defined valid distance range; and

replacing the subset of the N distance values with replacement distance values to yield a modified set of N distance values.