Video monitoring system with privacy features

Patent metadata

Field	Value
Publication number	US-12106647-B2
Application number	US-202318317044-A
Country	US
Kind code	B2
Filing date	May 12, 2023
Priority date	Sep 9, 2019
Publication date	Oct 1, 2024
Grant date	Oct 1, 2024

Abstract

A surveillance monitoring system may use a camera to detect any viewing faces visible within viewing sight of a monitor and determine whether the detected viewing faces belong to authorized individuals who are authorized to view video surveillance footage on the monitor or if any of the detected viewing faces belong to individuals who are not authorized to view video surveillance footage on the monitor. When the detected viewing faces belong only to authorized individuals, the surveillance monitoring system continues to display the video surveillance footage that includes identifiable faces without anonymizing the identifiable faces. When the detected viewing faces also include unauthorized individuals, the surveillance monitoring system may continue to display the video surveillance footage, but the surveillance monitoring system may automatically anonymize one or more of the identifiable faces seen in the video surveillance footage.

First claim

What is claimed is:

1. A method of displaying video surveillance footage on a display, the method comprising:
analyzing the video surveillance footage to identify an object in the video surveillance footage;
tracking the object over a plurality of frames of the video surveillance footage, wherein the plurality of frames in which the object is present and tracked are referred to as a plurality of object tracking frames;
identifying a unique characteristic of the tracked object in one or more of the plurality of object tracking frames while not being able to specifically identify the unique characteristic of the tracked object in one or more other of the plurality of object tracking frames of the video surveillance footage;
assigning a unique object ID to the tracked object in each of the one or more of the plurality of object tracking frames of the video surveillance footage in which the unique characteristic of the tracked object was identified;
assigning the unique object ID to the tracked object in each of the one or more other of the plurality of object tracking frames of the video surveillance footage in which the unique characteristic of the tracked object was not able to be identified;
determining whether the tracked object is part of a protected group or an unprotected group based at least in part on the identified unique characteristic of the tracked object;
displaying the plurality of object tracking frames of the video surveillance footage on the display, including:
when the tracked object is determined to be part of the unprotected group, not anonymizing at least part of the tracked object that is assigned the unique object ID in each of the plurality of object tracking frames including the one or more of the plurality of object tracking frames in which the unique characteristic of the tracked object was identified and the one or more other of the plurality of object tracking frames in which the unique characteristic of the tracked object was not able to be specifically identified; and
when the tracked object is determined to be part of the protected group, anonymizing at least part of the tracked object that is assigned the unique object ID in each of the plurality of object tracking frames including the one or more of the plurality of object tracking frames in which the unique characteristic of the tracked object was identified and the one or more other of the plurality of object tracking frames in which the unique characteristic of the tracked object was not able to be specifically identified.

2. The method of claim 1 , wherein the tracked object is a person, and the unique characteristic includes one or more facial characteristics of the person.

3. The method of claim 2 , wherein:
when the person is determined to be part of the unprotected group, the at least part of the person that is not anonymized includes the face of the person; and
when the person is determined to be part of the protected group, the at least part of the person that is anonymized includes the face of the person.

4. The method of claim 1 , further comprising:
identifying another object in one or more of the plurality of object tracking frames of the video surveillance footage in addition to the tracked object; and
displaying the plurality of object tracking frames of the video surveillance footage on the display includes anonymizing at least part of the other object that is identified in addition to the tracked object.

5. The method of claim 1 , further comprising:
identifying another object in one or more of the plurality of object tracking frames of the video surveillance footage in addition to the tracked object; and
displaying the plurality of object tracking frames of the video surveillance footage on the display includes not anonymizing at least part of the other object that is identified in addition to the tracked object.

6. The method of claim 1 , wherein the tracked object is a vehicle, and the unique characteristic includes a license plate number of the vehicle.

7. The method of claim 1 , wherein determining whether the tracked object is part of the protected group comprises:
comparing the unique characteristic of the tracked object with corresponding characteristics of each of a plurality of members of the protected group, and if there is a match, determining that the that tracked object is part of the protected group.

8. The method of claim 1 , wherein determining whether the tracked object is part of the unprotected group comprises:
comparing the unique characteristic of the tracked object with corresponding characteristics of each of a plurality of members of the unprotected group, and if there is a match, determining that the that tracked object is part of the unprotected group.

9. The method of claim 1 , wherein determining whether the tracked object is part of the protected group comprises:
comparing the unique characteristic of the tracked object with corresponding characteristics of each of a plurality of members of the unprotected group, and if there is no match, determining that the that tracked object is part of the protected group.

10. The method of claim 1 , wherein determining whether the tracked object is part of the unprotected group comprises:
comparing the unique characteristic of the tracked object with corresponding characteristics of each of a plurality of members of the protected group, and if there is no match, determining that the that tracked object is part of the unprotected group.

11. A system for displaying video surveillance footage comprising:
an input for receiving a video surveillance footage;
a display;
a controller operatively coupled to the input and the display, the controller configured to:
analyze the video surveillance footage received via the input to identify an object in the video surveillance footage;
track the object over a plurality of frames of the video surveillance footage, wherein the plurality of frames in which the object is present and tracked are referred to as a plurality of object tracking frames of the video surveillance footage;
identify a unique characteristic of the tracked object in one or more of the plurality of object tracking frames while not being able to specifically identify the unique characteristic of the tracked object in one or more other of the plurality of object tracking frames;
determine whether the tracked object is part of a protected group or an unprotected group based at least in part on the identified unique characteristic of the tracked object;
display on the display the plurality of object tracking frames of the video surveillance footage on the display, including:
when the tracked object is determined to be part of the unprotected group, not anonymizing at least part of the tracked object in each of the plurality of object tracking frames including the one or more of the plurality of object tracking frames in which the unique characteristic of the tracked object was identified and the one or more other of the plurality of object tracking frames in which the unique characteristic of the tracked object was not able to be specifically identified; and
when the tracked object is determined to be part of the protected group, anonymizing at least part of the tracked object in each of the plurality of object tracking frames including the one or more of the plurality of object tracking frames in which the unique characteristic of the tracked object was identified and the one or more other of the plurality of object tracking frames in which the unique characteristic of the tracked object was not able to be specifically identified.

12. The system of claim 11 , wherein the co

Assignees

• Honeywell Int Inc

Inventors

• Eswara Lalitha M
• Kattamuru Harika Sarvani
• Moosad Anagha
• Hanumegowda Bhavya
• Ganesan Balamurugan
• Kimber Jeremy
• Dhamija Vijay
• Shaik Ismaiel
• Jain Abhisekh

Classifications

• G06V40/173

  face re-identification, e.g. recognising unknown faces across different face tracks · CPC title

• G06V40/161

  Detection; Localisation; Normalisation · CPC title

• G06V20/52

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title

• H04N7/183

  for receiving images from a single remote source · CPC title

• G08B7/06

  using electric transmission {, e.g. involving audible and visible signalling through the use of sound and light sources} · CPC title