System and method for operating an intelligent videoframe privacy monitoring management system for videoconferencing applications

Patent metadata

Field	Value
Publication number	US-11838684-B2
Application number	US-202117159064-A
Country	US
Kind code	B2
Filing date	Jan 26, 2021
Priority date	Jan 26, 2021
Publication date	Dec 5, 2023
Grant date	Dec 5, 2023

Abstract

A system or method executing an intelligent videoframe privacy monitoring management system comprising a processor to execute code instructions of a multimedia multi-user collaboration application to join a videoconference session, a display screen, a speaker, a video camera, and a microphone where the video camera captures a videoframe of a user or background to be transmitted in the videoconference session and the processor to determine from input videoframe data and the detected sensor distance data of the user or the objects or inputting these into the intelligent videoframe privacy monitoring management system to generate optimized videoframe privacy adjustments to apply a privacy alteration to captured videoframes when the user is detected as absent, other faces, or background movement is detected.

First claim

What is claimed is:

1. An information handling system executing an intelligent videoframe privacy monitoring management system comprising:
a processor configured to execute code instructions of a multimedia multi-user collaboration application to join a videoconference session with a remotely located computing device;
a display screen, a speaker, a video camera, and a microphone;
the video camera system configured to capture videoframes of a user and background in the videoconference session;
the processor to execute code instructions of a user presence detection module with sensor data, including the video camera system, time of flight (TOF) sensor, or a microphone, to detect distance data for the user or objects in front of the video camera system;
the processor to input videoframes and the detected distance data from the user presence detection module of the user or the objects, to a trained neural network of the intelligent videoframe privacy monitoring management system to use the detected proximity sensor distance data to identify the presence or absence of the user and the videoframe data to identify the user;
the processor to execute code instructions the intelligent videoframe privacy monitoring management system to output determination of the user's presence or absence, to identify an image of the user as a videoconference participant, and then to generate an optimized videoframe privacy adjustment correlated to the user's absence, where the optimized videoframe privacy adjustment includes generating AV processing instruction adjustment to apply a privacy alteration to captured videoframes when the user is detected as absent even when another person not identified as the user is present; and
a network interface device configured to transmit a processed, encoded media sample, including the captured videoframes with any applied privacy alteration to a remotely located computing device participating in the videoconference session.

2. The information handling system of claim 1 further comprising:
the (TOF) sensor device to detect distance data of the user or the background from the video camera system.

3. The information handling system of claim 1 , wherein the optimized videoframe privacy adjustment includes replacing the captured videoframes with a stock photo as the AV processing instruction adjustment for transmission when the user is detected as absent.

4. The information handling system of claim 1 , wherein the optimized videoframe privacy adjustments includes executing a virtual background AV processing instruction module to apply a virtual background to the captured videoframes as the AV processing instruction adjustment when the user is detected as absent.

5. The information handling system of claim 1 , wherein the optimized videoframe privacy adjustments includes executing a blurring AV processing instruction module to blur the captured videoframes as the AV processing instruction adjustment when the user is detected as absent.

6. The information handling system of claim 1 further comprising:
the processor to execute code instructions for the trained neural network to detect a return presence of the user in front of the video camera system after the user is detected as absent via detected distance data; and
the processor to end the applied optimized videoframe privacy adjustment to the captured video frames for transmission.

7. The information handling system of claim 1 further comprising:
the processor to execute code instructions of the intelligent videoframe privacy monitoring management system to output a determination of plural detected faces or background movement in front of the video camera system and to generate an optimized videoframe privacy adjustment, where the optimized videoframe privacy adjustment includes generating AV processing instruction adjustment to apply a privacy alteration to captured videoframes when plural detected faces or background movement is detected.

8. The information handling system of claim 1 further comprising:
the processor to execute code instructions to identify a single face and no background movement behind the user; and
the processor to end the applied optimized videoframe privacy adjustment to the captured video frames for transmission.

9. The information handling system of claim 1 further comprising:
the processor to execute code instructions of a trained neural network of the intelligent videoframe privacy monitoring management system to output determination of a user's presence or absence and identity recognition of the user's face, and to generate an optimized videoframe privacy adjustment correlated to the user's absence or presence, the identity recognition of the user's face, where the optimized videoframe privacy adjustment includes generating AV processing instruction adjustment to apply a privacy alteration to captured videoframes when the user is detected as absent or end the privacy alteration when the user is identified and detected as present.

10. A method for intelligently managing a user's appearance in a collaboration videoconference session for an information handling system, comprising:
executing code instructions of a multimedia multi-user collaboration application, via a processor, to join a videoconference session with a remotely located computing device;
capturing videoframe of a user and background, via a video camera, in the videoconference session;
detecting, with a proximity sensor, distance data for the user and objects in front of the video camera;
inputting videoframe data and the detected proximity sensor distance data of the user and the objects to the intelligent videoframe privacy monitoring management system to use the detected proximity sensor distance data to identify the presence or absence of the user and the videoframe data to identify the user;
executing code instructions of the intelligent videoframe privacy monitoring management system to output determination of the user's presence or absence, to identify an image of the user as a videoconference participant, and to generate an optimized videoframe privacy adjustment correlated to the user's absence based on the distance data even when another person not identified as the user is present, where the optimized videoframe privacy adjustment includes generating AV processing instruction adjustment to apply a privacy alteration to captured videoframes when the user is detected as absent even when the another person is present before the video camera; and
transmitting, via a network interface device, a processed, encoded media sample, including the captured videoframes with any applied privacy alteration, to a remotely located computing device participating in the videoconference session.

11. The method of claim 10 further comprising:
replacing the captured videoframes to be transmitted with a stock user image as the optimized videoframe privacy adjustment when the user is detected as absent.

12. The method of claim 10 further comprising:
ending the optimized videoframe privacy adjustment returning to the previous AV processing settings for the captured videoframes to be transmitted when a trained neural network of the intelligent videoframe privacy monitoring management system outputs a determination of the user's presence.

13. The method of claim 10 further comprising:
executing a virtual background AV processing instruction module to apply a virtual background to the captured videoframes to be transmitted as the optimized videoframe privacy adjustment when the user is detected as absent.

14. The method of claim 10 further comprising:
executing code instr

Assignees

• Dell Products Lp

Inventors

• Swierk Todd E
• Viswanathan Iyer Vivek

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• H04N7/147 Primary

  Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals (selecting H04Q) · CPC title

• G06N3/08

  Learning methods · CPC title

• G06T5/002

  Physics · mapped topic