Automated privacy adjustments to video conferencing streams

Patent metadata

Field	Value
Publication number	US-9313454-B2
Application number	US-201114124522-A
Country	US
Kind code	B2
Filing date	Oct 1, 2011
Priority date	Jun 7, 2011
Publication date	Apr 12, 2016
Grant date	Apr 12, 2016

Abstract

Methods and systems may involve determining a user attention level based on video stream data associated with a first participant in an always-on video conferencing session. The video stream data may be modified based on the user attention level to obtain modified video stream data that is automatically adjusted for privacy. In addition, the modified video stream data may be transmitted to one or more other participants in the video conferencing session.

First claim

We claim:

1. A system comprising:
an image capture device to obtain first video stream data associated with a first participant in a video conferencing session; and
logic to,
determine a user attention level based at least on whether a front-facing face is detected in the first video stream data,
modify the first video stream data based at least on the user attention level to obtain modified video stream data, and
transmit the modified video stream data to a second participant in the video conferencing session,

wherein the logic is to,
increment an attention measure by a first gain if the user attention level indicates that the first participant is paying attention to the video conferencing session, and
decrement the attention measure by a second gain if the user attention level indicates that the first participant is not paying attention to the video conferencing session, wherein the first video stream data is to be modified based at least on the attention measure.

2. The system of claim 1 , wherein the image capture device includes a two-dimensional (2D) component and a depth capture component, and the logic is to identify 2D information and depth information in the first video stream data.

3. The system of claim 2 , wherein the depth capture component includes:
a structured light emitter operative in the IR spectrum; and
an IR camera to capture an IR image, wherein the logic is to identify the depth information based at least on the IR image.

4. The system of claim 2 , wherein the logic is to,
use the depth information to identify one or more candidate face regions,
extract the one or more candidate face regions from the first video stream data, and
conduct a face recognition analysis on the one or more candidate face regions.

5. The system of claim 4 , wherein the logic is to use a front-facing face as a signifier of attention in the face recognition analysis.

6. The system of claim 1 , wherein the first gain is to be greater than the second gain.

7. The system of claim 1 , wherein the logic is to modify at least one of a blur characteristic and a contrast characteristic of the first video stream data based at least on the attention measure.

8. The system of claim 1 , wherein the logic is to modify an audio volume of the video stream data based at least on the attention measure.

9. The system of claim 1 , further including a network controller, wherein the logic is to transmit the modified video stream data to the second participant via the network controller.

10. The system of claim 9 , wherein the network controller is to transmit the modified video stream data to a plurality of participants in the video conferencing session.

11. The system of claim 1 , further including a display to output second video stream data associated with the second participant in the video conferencing session.

12. A computer implemented method comprising:
determining a user attention level based at least on whether a front-facing face is detected in video stream data associated with a first participant in a video conferencing session;
modifying the video stream data based at least on the user attention level to obtain modified video stream data;
transmitting the modified video stream data to a second participant in the video conferencing session;
incrementing an attention measure by a first gain if the user attention level indicates that the first participant is paying attention to the video conferencing session; and
decrementing the attention measure by a second gain if the user attention level indicates that the first participant is not paying attention to the video conferencing session, wherein modifying the video stream data includes modifying the video stream data based at least on the attention measure.

13. The method of claim 12 , further including identifying two-dimensional (2D) information and depth information in the video stream data.

14. The method of claim 13 , wherein the depth information includes infrared (IR) information.

15. The method of claim 13 , wherein determining the user attention level includes:
using the depth information to identify one or more candidate face regions;
extracting the one or more candidate face regions from the video stream data; and
conducting a face recognition analysis on the one or more candidate face regions.

16. The method of claim 15 , further including using a front-facing face as a signifier of attention in the face recognition analysis.

17. The method of claim 12 , wherein the first gain is greater than the second gain.

18. The method of claim 12 , wherein modifying the video stream data includes modifying at least one of a blur characteristic and a contrast characteristic of the video stream data based at least on the attention measure.

19. The method of claim 12 , wherein modifying the video stream data includes modifying an audio volume of the video stream data based at least on the attention measure.

20. A non-transitory computer readable storage medium comprising a set of instructions which, if executed by a processor, cause a computer to:
determine a user attention level based at least on whether a front-facing face is detected in video stream data associated with a first participant in a video conferencing session;
modify the video stream data based at least on the user attention level to obtain modified video stream data;
transmit the modified video stream data to a second participant in the video conferencing session;
increment an attention measure by a first gain if the user attention level indicates that the first participant is paying attention to the video conferencing session; and
decrement the attention measure by a second gain if the user attention level indicates that the first participant is not paying attention to the video conferencing session, wherein the video stream data is to be modified based at least on the attention measure.

21. The medium of claim 20 , wherein the instructions, if executed, cause a computer to identify two-dimensional (2D) information and depth information in the video stream data.

22. The medium of claim 21 , wherein the depth information is to include infrared (IR) information.

23. The medium of claim 21 , wherein the instructions, if executed, cause a computer to:
use the depth information to identify one or more candidate face regions,
extract the one or more candidate face regions from the video stream data; and
conduct a face recognition analysis on the one or more candidate face regions.

24. The medium of claim 21 , wherein the instructions, if executed, cause a computer to use a front-facing face as a signifier of attention in the face recognition analysis.

25. The medium of claim 20 , wherein the first gain is to be greater than the second gain.

26. The medium of claim 20 , wherein the instructions, if executed, cause a computer modify at least one of a blur characteristic and a contrast characteristic of the video stream data based at least on the attention measure.

27. The medium of claim 20 , wherein the instructions, if executed, cause a computer to modify an audio volume of the video stream data based at least on the attention measure.

28. The system of claim 1 , wherein the logic is to modify an audio volume of the video stream data based at least on the attention level.

29. The method of claim 12 ,

Assignees

• Lalonde Paul
• Carmean Douglas
• Intel Corp

Inventors

• Lalonde Paul
• Carmean Douglas

Classifications

• H04N23/20

  for generating image signals from infrared radiation only · CPC title

• H04N7/147

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

• H04N7/15 Primary

  Conference systems · CPC title

• H04N5/33

  Transforming infrared radiation (cameras or camera modules for generating image signals from infrared radiation H04N23/20; circuitry of SSIS for transforming infrared radiation into image signals H04N25/20) · CPC title

• G06K9/00221

  Physics · mapped topic