Computer system and method for improving security screening

• US 10,366,293 B1
• Filed: 08/23/2018
• Issued: 07/30/2019
• Est. Priority Date: 04/24/2018
• Status: Active Grant

• Current Assignee: Rapiscan Laboratories Incorporated (OSI Systems Incorporated)
• Original Assignee: Synapse Technology Corporation (Palantir Technologies Incorporated)
• Inventors: Faviero, Bruno Brasil Ferrari, Gautam, Simanta, Cinnamon, Ian
• Primary Examiner(s): Hon, Ming Y
• Application Number:
  US16/110,605
• Time in Patent Office: 341 Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

In an example, a computing device comprises at least one processor, a memory, and a non-transitory computer-readable storage medium storing instructions thereon that, when executed, cause the at least one processor to perform functions comprising: performing an initial security screening on an object based on a first set of security-related data associated with the object and a first set of security screening parameters, and performing a supplemental security screening on the object based on a second set of security-related data associated with the object and a second set of security screening parameters. The first set of security-related data may be different from the second set of security-related data, and the first set of security screening parameters may be different from the second set of security screening parameters.

Claims

1. A computing system comprising:

at least one processor; and

a non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by the at least one processor, cause the computing system to;

perform an initial security screening on an object based on (i) a first set of security-related data associated with the object comprising first image data corresponding to a first scan of the object by a detection device communicatively coupled to the computing system and (ii) a first set of security screening parameters, wherein performing the initial security screening comprises;

based on the first image data, executing a neural network in accordance with the first set of security screening parameters; and

based on executing the neural network in accordance with the first set of security screening parameters, generating a first security determination for the object;

perform a supplemental security screening on the object based on (i) a second set of security-related data associated with the object comprising at least one of (a) the first image data or (b) second image data corresponding to a second scan of the object and iii) a second set of security screening parameters, wherein performing the supplemental security screening comprises;

based on at least one of (a) the first image data or (b) the second image data, executing a neural network in accordance with the second set of security screening parameters; and

based on executing the neural network in accordance with the second set of security screening parameters, generating a second security determination for the object; and

provide to a computing device an output notification based on at least one of (i) the first security determination or (ii) the second security determination; and

wherein the first set of security-related data is different from the second set of security-related data, and wherein the first set of security screening parameters is different from the second set of security screening parameters.

2. The computing system of claim 1, wherein performing the initial security screening further comprises, based on executing the neural network in accordance with the first set of security screening parameters, performing object detection on the first image data to determine whether a class of item can be identified from the first image data, and wherein performing the supplemental security screening further comprises, based on executing the neural network in accordance with the second set of security screening parameters, performing object detection on the at least one of the first image data or the second image data to determine whether a class of item can be identified from the at least one of the first image data or the second image data.

3. The computing system of claim 2, wherein the first and second set of security screening parameters comprise an object detection confidence level upon which the object detection is based.

4. The computing system of claim 1, wherein the instructions, when executed by the at least one processor, further cause the computing system to:

determine that a false positive rate for performing object detection has changed; and

based on the determination that the false positive rate has changed, adjust a security screening parameter of one or both of the first set of security screening parameters and the second set of security screening parameters, wherein the security screening parameter comprises an object detection confidence level for performing the object detection.

5. The computing system of claim 1, wherein the second set of security-related data comprises at least some security-related data that was not available during the initial security screening.

6. The computing system of claim 1, wherein the detection device communicatively coupled to the computing system is located at a departure security checkpoint;

wherein the second security determination for the object comprises a determination that the object violates a condition, wherein the condition comprises at least one of a customs-related condition or a security-related condition; and

wherein providing to the computing device the output notification based on at least one of (i) the first security determination or (ii) the second security determination comprises providing to a computing device located at an arrival location an output notification that indicates the violated condition.

7. The computing system of claim 6, wherein the output notification comprises an indication of at least one of:

(1) passenger itinerary data associated with the object, (2) passenger identification data associated with the object, or (3) a location within the object corresponding to the violated security-related condition.

8. The computing system of claim 1, wherein the output notification provides an indication that the object contains an item known not to pose a security threat.

9. The computing system of claim 1, wherein the instructions, when executed by the at least one processor, further cause the computing system to:

determine that a security-related condition has changed; and

change at least one of the first security screening parameters or the second set of security screening parameters based on the determination that the security-related condition has changed.

10. The computing system of claim 9, wherein the changed security-related condition comprises at least one of:

an increase in object screening throughput, a change in a security threat level, or a change in a class of item to be detected.

11. A method comprising:

performing an initial security screening on an object based on (i) a first set of security-related data associated with the object comprising first image data corresponding to a first scan of the object by a detection device communicatively coupled to the computing system and (ii) a first set of security screening parameters, wherein performing the initial security screening comprises;

based on the first image data, executing a neural network in accordance with the first set of security screening parameters; and

based on executing the neural network in accordance with the first set of security screening parameters, generating a first security determination for the object;

performing a supplemental security screening on the object based on (i) a second set of security-related data associated with the object comprising at least one of (a) the first image data or (b) second image data corresponding to a second scan of the object and (ii) a second set of security screening parameters, wherein performing the supplemental security screening comprises;

based on at least one of (a) the first image data or (b) the second image data, executing a neural network in accordance with the second set of security screening parameters; and

based on executing the neural network in accordance with the second set of security screening parameters, generating a second security determination for the object; and

providing to a computing device an output notification based on at least one of (i) the first security determination or (ii) the second security determination; and

wherein the first set of security-related data is different from the second set of security-related data, and wherein the first set of security screening parameters is different from the second set of security screening parameters.

12. The method of claim 11, wherein performing the initial security screening comprises, based on executing the neural network in accordance with the first set of security screening parameters, performing object detection on the first image data to determine whether a class of item can be identified from the first image data, and wherein performing the supplemental security screening further comprises, based on executing the neural network in accordance with the second set of security screening parameters, performing object detection on the at least one of the first image data or the second image data to determine whether a class of item can be identified from the at least one of the first image data or the second image data.

13. The method of claim 11, further comprising:

determining that a false positive rate for performing object detection has changed; and

based on the determination that the false positive rate has changed, adjusting a security screening parameter of one or both of the first set of security screening parameters and the second set of security screening parameters, wherein the security screening parameter comprises an object detection confidence level for performing the object detection.

14. The method of claim 11, further comprising:

determining that a security-related condition has changed; and

changing at least one of the first security screening parameters or the second set of security screening parameters based on the determination that the security-related condition has changed.

15. The method of claim 14, wherein the changed security-related condition comprises at least one of:

an increase in object screening throughput, a change in a security threat level, or a change in a class of item to be detected.

16. A tangible non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, cause a computing system to:

perform an initial security screening on an object based on (i) a first set of security-related data associated with the object comprising first image data corresponding to a first scan of the object by a detection device communicatively coupled to the computing system and (ii) a first set of security screening parameters, wherein performing the initial security screening comprises;

based on the first image data, executing a neural network in accordance with the first set of security screening parameters; and

based on executing the neural network in accordance with the first set of security screening parameters, generating a first security determination for the object;

perform a supplemental security screening on the object based on (i) a second set of security-related data associated with the object comprising at least one of (a) the first image data or (b) second image data corresponding to a second scan of the object and (ii) a second set of security screening parameters, wherein performing the supplemental security screening comprises;

based on at least one of (a) the first image data or (b) the second image data, executing a neural network in accordance with the second set of security screening parameters; and

based on executing the neural network in accordance with the second set of security screening parameters, generating a second security determination for the object; and

provide to a computing device an output notification based on at least one of (i) the first security determination or (ii) the second security determination; and

wherein the first set of security-related data is different from the second set of security-related data, and wherein the first set of security screening parameters is different from the second set of security screening parameters.

17. The non-transitory computer-readable storage medium of claim 16, wherein performing the initial security screening further comprises, based on executing the neural network in accordance with the first set of security screening parameters, performing object detection on the first image data to determine whether a class of item can be identified from the first image data, and wherein performing the supplemental security screening further comprises, based on executing the neural network in accordance with the second set of security screening parameters, performing object detection on the at least one of the first image data or the second image data to determine whether a class of item can be identified from the at least one of the first image data or the second image data.

18. The non-transitory computer-readable storage medium of claim 16, wherein the instructions, when executed by the at least one processor, further cause the computing system to:

determine that a false positive rate for performing object detection has changed; and

based on the determination that the false positive rate has changed, adjust a security screening parameter of one or both of the first set of security screening parameters and the second set of security screening parameters, wherein the security screening parameter comprises an object detection confidence level for performing the object detection.

19. The non-transitory computer-readable storage medium of claim 16, wherein the instructions, when executed by the at least one processor, further cause the computing system to:

determine that a security-related condition has changed; and

change at least one of the first security screening parameters or the second set of security screening parameters based on the determination that the security-related condition has changed.

20. The non-transitory computer-readable storage medium of claim 19, wherein the changed security-related condition comprises at least one of:

an increase in object screening throughput, a change in a security threat level, or a change in a class of item to be detected.