Computerized system and method for adaptive stranger detection

Patent metadata

Field	Value
Publication number	US-12026596-B2
Application number	US-202117462387-A
Country	US
Kind code	B2
Filing date	Aug 31, 2021
Priority date	Sep 17, 2019
Publication date	Jul 2, 2024
Grant date	Jul 2, 2024

Abstract

Disclosed are systems and methods for improving interactions with and between computers in computerized security and content monitoring, hosting and providing devices, systems and/or platforms. The disclosed systems and methods provide a novel framework that adaptively distinguishes between known people versus unknown people based on a dynamically applied, anonymous facial recognition methodology. The disclosed framework provides such functionality by recognizing faces within captured images without storing any information or annotations regarding or revealing the captured person's identity. The framework is configured to adaptively learn to distinguish between faces seen for the first time and faces it has previously seen by locally processing a captured image and only sending face embeddings to a network location for future comparisons of subsequently, anonymously captured images.

First claim

What is claimed is:

1. A method comprising:
identifying, by a device, an image comprising content depicting a person currently at a location;
analyzing, by the device, the image, and determining information indicating facial characteristics of the person;
comparing, by the device, the face information to a set of face embeddings stored in a gallery hosted by storage, each stored face embedding comprising face information for previous person depictions captured at the location;
determining, by the device, that the person is a stranger based on the comparison;
updating, via the device, the gallery based on the stranger determination, updating the gallery comprising storing the face information as new face embedding data within the gallery, said storage comprising inserting the new face embedding data into a first position within the gallery and moving each previously stored face embedding down a position; and
communicating, by the device, an alert to equipment at the location based on the stranger determination, the alert indicating additional security protocols that are to be implemented until further input, wherein the updated gallery includes face information of the person to avoid a subsequent alert in connection with the person.

2. The method of claim 1 , further comprising:
identifying at least one user associated with the location; and
communicating an alert to a device of the identified user based on the stranger determination, the communicated alert comprising information identifying the determined stranger.

3. The method of claim 1 , further comprising:
making a determination that a second person currently at the location is a known person; and
updating the gallery based on the known person determination by identifying stored face information for the known person, and increasing a value corresponding to a frequency or recency of detections of the known person at the location.

4. The method of claim 1 , further comprising:
analyzing the image, and identifying the face of the person within the content of the image; and
cropping the image based on the identified face, wherein the analysis of the image is based on the cropped image.

5. A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions, that when executed by a device, perform a method comprising:
identifying, by the device, an image comprising content depicting a person currently at a location;
analyzing, by the device, the image, and determining information indicating facial characteristics of the person;
comparing, by the device, the face information to a set of face embeddings stored in a gallery hosted by storage, each stored face embedding comprising face information for previous person depictions captured at the location;
determining, by the device, that the person is a stranger based on the comparison;
updating, via the device, the gallery based on the stranger determination, updating the gallery comprising storing the face information as new face embedding data within the gallery, said storage comprising inserting the new face embedding data into a first position within the gallery and moving each previously stored face embedding down a position; and
communicating, by the device, an alert to equipment at the location based on the stranger determination, the alert indicating additional security protocols that are to be implemented until further input, wherein the updated gallery includes face information of the person to avoid a subsequent alert in connection with the person.

6. The method of claim 1 , wherein the equipment comprises at least one of a device, a door, a lock and an alarm associated with the location.

7. The method of claim 6 , wherein the additional security protocols comprise at least one of locking the device, locking the door, locking the lock and sounding the alarm.

8. The method of claim 1 , further comprising:
determining that the insertion of the new face embedding data causes the gallery to exceed a predetermined size;
identifying face embedding data at the last position in the gallery; and
deleting the identified face embedding data.

9. The method of claim 8 , wherein the predetermined size of the gallery is based on a type of the location.

10. The non-transitory computer-readable storage medium of claim 5 , further comprising:
determining that the insertion of the new face embedding data causes the gallery to exceed a predetermined size;
identifying face embedding data at the last position in the gallery; and
deleting the identified face embedding data.

11. The non-transitory computer-readable storage medium of claim 5 , further comprising:
identifying at least one user associated with the location; and
communicating an alert to a device of the identified user based on the stranger determination, the communicated alert comprising information identifying the determined stranger.

12. The non-transitory computer-readable storage medium of claim 5 , further comprising:
making a determination that a second person currently at the location is a known person; and
updating the gallery based on the known person determination by identifying stored face information for the known person, and increasing a value corresponding to a frequency or recency of detections of the known person at the location.

13. The non-transitory computer-readable storage medium of claim 5 , further comprising:
analyzing the image, and identifying the face of the person within the content of the image; and
cropping the image based on the identified face, wherein the analysis of the image is based on the cropped image.

14. The non-transitory computer-readable storage medium of claim 5 , wherein the equipment comprises at least one of a device, a door, a lock and an alarm associated with the location.

15. The non-transitory computer-readable storage medium of claim 14 , wherein the additional security protocols comprise at least one of locking the device, locking the door, locking the lock and sounding the alarm.

16. A device comprising:
a processor configured to:
identify an image comprising content depicting a person currently at a location;
analyze the image, and determine information indicating facial characteristics of the person;
compare the face information to a set of face embeddings stored in a gallery hosted by storage, each stored face embedding comprising face information for previous person depictions captured at the location;
determine that the person is a stranger based on the comparison;
update the gallery based on the stranger determination, updating the gallery comprising storing the face information as new face embedding data within the gallery, said storage comprising inserting the new face embedding data into a first position within the gallery and moving each previously stored face embedding down a position; and
communicate an alert to equipment at the location based on the stranger determination, the alert indicating additional security protocols that are to be implemented until further input, wherein the updated gallery includes face information of the person to avoid a subsequent alert in connection with the person.

17. The device of claim 16 , wherein the equipment comprises at least one of a device, a door, a lock and an alarm associated with the location.

18. The device of claim 17 , wherein the additional security protocols comprise at least one of locking the device, locking the door, locking the lock and sounding the alarm.

Assignees

• Verizon Patent & Licensing Inc

Inventors

• Zhang Yang
• Dassa Guy
• Lahtiranta Atte

Classifications

• G06V40/168

  Feature extraction; Face representation · CPC title

• G06V10/449

  Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters · CPC title

• G06V10/7715

  Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods · CPC title

• G06V10/761

  Proximity, similarity or dissimilarity measures · CPC title

• G06V40/50

  Maintenance of biometric data or enrolment thereof · CPC title