Preserving privacy in surveillance

Patent metadata

Field	Value
Publication number	US-10798313-B2
Application number	US-201816109263-A
Country	US
Kind code	B2
Filing date	Aug 22, 2018
Priority date	Aug 22, 2017
Publication date	Oct 6, 2020
Grant date	Oct 6, 2020

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for preserving privacy in surveillance. The methods, systems, and apparatus include actions of obtaining images of a scene captured by a camera, identifying an object in the images through object recognition, determining that the object that is identified in the images is of a particular type that has a privacy restriction, and in response to determining that the object in the images is of the particular type that has the privacy restriction, obfuscating an appearance of the object in the images.

First claim

What is claimed is:

1. A computer-implemented method comprising:
obtaining images of a scene captured by a camera;
identifying an object in the images through object recognition;
determining that (i) the object that is identified in the images is of a particular type that has a privacy restriction and (ii) a person is interacting with the object; and
in response to determining that (i) the object in the images is of the particular type that has the privacy restriction and (ii) the person is interacting with the object, obfuscating an appearance of the object in the images and not obfuscating other portions of the images.

2. The method of claim 1 , wherein determining that (i) the object that is identified in the images is of a particular type that has a privacy restriction and (ii) a person is interacting with the object comprises:
obtaining a list of types of objects that are sensitive;
determining that the object identified in the images is included in the list of types of objects that are sensitive; and
in response to determining that the object identified in the images is included in the list of types of objects that are sensitive, determining that the object in the images is of a particular type that has a privacy restriction.

3. The method of claim 1 , wherein identifying an object in the images through object recognition comprises:
determining a privacy region in the images,
wherein identifying the object in the images is from performing object recognition in only the privacy region in the images.

4. The method of claim 1 , wherein determining that (i) the object that is identified in the images is of a particular type that has a privacy restriction and (ii) a person is interacting with the object comprises:
determining that the object that is identified in the images is of the particular type that has a privacy restriction; and
in response to determining that the object that is identified in the images is of the particular type that has a privacy restriction, determining that the person is interacting with the object.

5. The method of claim 4 , wherein determining that the person is interacting with the object comprises:
identifying a hand in the images; and
determining that the hand is touching the object.

6. The method of claim 4 , comprising:
determining that a person has stopped interacting with the object; and
in response to determining that a person has stopped interacting with the object, stopping obfuscation of an appearance of the object in the images.

7. The method of claim 1 , wherein determining that (i) the object that is identified in the images is of a particular type that has a privacy restriction and (ii) a person is interacting with the object comprises:
determining that a state of the object has changed based on a change in the appearance of the object; and
wherein obfuscating the appearance of the object in the images is in response to determining that the state of the object has changed based on the change in the appearance of the object.

8. The method of claim 1 , wherein obfuscating an appearance of the object in the images comprises pixel-scrambling pixels that represent the object in the images.

9. The method of claim 1 , wherein obfuscating an appearance of the object in the images comprises using blur-kernels on pixels that represent the object in the images.

10. The method of claim 1 , wherein the object comprises a keypad, a personal computer, an automated teller machine, a credit card reader, a cash register, an access control panel, a computer monitor, a tablet display, a phone display, a credit card, a driver's license, a photo identification, or a passport.

11. A system comprising:
one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
obtaining images of a scene captured by a camera;
identifying an object in the images through object recognition;
determining that (i) the object that is identified in the images is of a particular type that has a privacy restriction and (ii) a person is interacting with the object; and
in response to determining that (i) the object in the images is of the particular type that has the privacy restriction and (ii) the person is interacting with the object, obfuscating an appearance of the object in the images and not obfuscating other portions of the images.

12. The system of claim 11 , wherein determining that (i) the object that is identified in the images is of a particular type that has a privacy restriction and (ii) a person is interacting with the object comprises:
obtaining a list of types of objects that are sensitive;
determining that the object identified in the images is included in the list of types of objects that are sensitive; and
in response to determining that the object identified in the images is included in the list of types of objects that are sensitive, determining that the object in the images is of a particular type that has a privacy restriction.

13. The system of claim 11 , wherein identifying an object in the images through object recognition comprises:
determining a privacy region in the images,
wherein identifying the object in the images is from performing object recognition in only the privacy region in the images.

14. The system of claim 11 , wherein determining that (i) the object that is identified in the images is of a particular type that has a privacy restriction and (ii) a person is interacting with the object comprises:
determining that the object that is identified in the images is of the particular type that has a privacy restriction; and
in response to determining that the object that is identified in the images is of the particular type that has a privacy restriction, determining that the person is interacting with the object.

15. The system of claim 14 , wherein determining that the person is interacting with the object comprises:
identifying a hand in the images; and
determining that the hand is touching the object.

16. The system of claim 14 , comprising:
determining that a person has stopped interacting with the object; and
in response to determining that a person has stopped interacting with the object, stopping obfuscation of an appearance of the object in the images.

17. The system of claim 11 , wherein determining that (i) the object that is identified in the images is of a particular type that has a privacy restriction and (ii) a person is interacting with the object comprises:
determining that a state of the object has changed based on a change in the appearance of the object; and
wherein obfuscating the appearance of the object in the images is in response to determining that the state of the object has changed based on the change in the appearance of the object.

18. The system of claim 11 , wherein obfuscating an appearance of the object in the images comprises pixel-scrambling pixels that represent the object in the images.

19. The system of claim 11 , wherein obfuscating an appearance of the object in the images comprises using blur-kernels on pixels that represent the object in the images.

20. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:
obtaining images of a scene captured by a camera;
identifying an object in the ima

Assignees

• Alarm Com Inc

Inventors

• Hutz David James
• Beach Allison
• Ramanathan Narayanan
• Berg Benjamin Asher
• Silverman Christopher
• Madden Donald

Classifications

• H04N5/2621 Primary

  Cameras specially adapted for the electronic generation of special effects during image pickup, e.g. digital cameras, camcorders, video cameras having integrated special effects capability · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V40/107

  Static hand or arm · CPC title

• H04N7/188 Primary

  Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position (signal generation from motion picture films H04N5/253) · CPC title

• G06F18/2414

  Smoothing the distance, e.g. radial basis function networks [RBFN] · CPC title