Authenticaton of rgb video based on infrared and depth sensing

Patent metadata

Field	Value
Publication number	US-2022284228-A1
Application number	US-202117192566-A
Country	US
Kind code	A1
Filing date	Mar 4, 2021
Priority date	Mar 4, 2021
Publication date	Sep 8, 2022
Grant date	—

Abstract

In one aspect, a device may include at least one processor and storage accessible to the at least one processor. The storage may include instructions executable by the at least one processor to access a first frame of RGB video content corresponding to a first time, access a first frame of IR video content corresponding to the first time, and access data from a depth sensor corresponding to the first time. The instructions may also be executable to determine whether at least a portion of the first frame of the RGB video content correlates to at least a portion of the first frame of the IR video content and/or the data from the depth sensor. Responsive to a determination that it does, the instructions may be executable to authenticate the RGB video content and indicate the RGB video content as being authenticated via a graphical user interface.

First claim

What is claimed is:

1 . A first device, comprising:
at least one processor; and storage accessible to the at least one processor and comprising instructions executable by the at least one processor to: access a first frame of red green blue (RGB) video content, the first frame of the RGB video content corresponding to a first time; access a first frame of infrared (IR) video content, the first frame of the IR video content corresponding to the first time; access data from a depth sensor, the data corresponding to the first time; compare the first frame of the RGB video content to one or more of the first frame of the IR video content and the data from the depth sensor to determine whether a match can be identified at least to within a threshold level of confidence; and responsive to a determination that a match has been identified at least to within the threshold level of confidence, authenticate the RGB video content for at least a first amount of time and indicate the RGB video content as being authenticated via a graphical user interface (GUI) presented on a display.

2 . The first device of claim 1 , wherein the instructions are executable to:
access the first frame of the IR video content and the data from the depth sensor via a side channel different from another channel through which the RGB video content is being communicated to the first device.

3 . The first device of claim 1 , wherein the instructions are executable to:
compare the first frame of the RGB video content at least to the first frame of the IR video content to determine whether a match can be identified at least to within the threshold level of confidence; and responsive to a determination that a match has been identified at least to within the threshold level of confidence at least using the first frame of the RGB video content and the first frame of the IR video content, authenticate the RGB video content for at least the first amount of time and indicate the RGB video content as being authenticated via the GUI presented on the display.

4 . The first device of claim 1 , wherein the instructions are executable to:
compare the first frame of the RGB video content at least to the data from the depth sensor to determine whether a match can be identified at least to within the threshold level of confidence using the first frame of the RGB video content and the data from the depth sensor; and responsive to a determination that a match has been identified at least to within the threshold level of confidence at least using the first frame of the RGB video content and the data from the depth sensor, authenticate the RGB video content for at least the first amount of time and indicate the RGB video content as being authenticated via the GUI presented on the display.

5 . The first device of claim 1 , wherein the instructions are executable to:
compare the first frame of the RGB video content to both the first image of the IR video content and the data from the depth sensor to determine whether a match can be identified at least to within the threshold level of confidence using the first frame of the RGB video content, the first frame of the IR video content, and the data from the depth sensor; and responsive to a determination that a match has been identified at least to within the threshold level of confidence at least using the first frame of the RGB video content, the first frame of the IR video content, and the data from the depth sensor, authenticate the RGB video content for at least the first amount of time and indicate the RGB video content as being authenticated via the GUI presented on the display.

6 . The first device of claim 1 , wherein the match relates to the matching of one or more boundaries indicated in the first images and data.

7 . The first device of claim 1 , wherein the match relates to matching features of the face of a person indicated in the first frame of the RGB video content and indicated in one or more of: the data from the depth sensor, the first frame of the IR video content.

8 . The first device of claim 1 , wherein the first amount of time is no more than one second.

9 . The first device of claim 1 , wherein the threshold level of confidence is at least ninety percent or above.

10 . The first device of claim 1 , wherein the depth sensor comprises a time-of-flight depth sensor selected from the group consisting of: a laser rangefinder, an IR rangefinder.

11 . The first device of claim 10 , comprising the depth sensor and comprising an IR camera that generates the IR video content.

12 . The first device of claim 1 , wherein the first device comprises a server that facilitates a video conference, wherein the RGB video content indicates a participant of the video conference, and wherein the server receives, from a second device different from the first device, the first frame of the RGB video content, the first frame of the IR video content, and the data from the depth sensor.

13 . A computer-implemented method, comprising:
accessing, at a first device, a first frame of red green blue (RGB) video content, the first frame of the RGB video content corresponding to a first time; accessing, at the first device, a first frame of infrared (IR) video content, the first frame of the IR video content corresponding to the first time; accessing, at the first device, data from a depth sensor, the data corresponding to the first time; determining, using the first device, whether a match can be identified at least to within a threshold level of confidence based on the first frame of the RGB video content and one or more of: the first frame of the IR video content, the data from the depth sensor; and responsive to determining that a match has been identified at least to within the threshold level of confidence, using the first device to authenticate the RGB video content for at least a first amount of time.

14 . The method of claim 13 , comprising:
indicating, using the first device, the RGB video content as being authenticated via a graphical user interface (GUI).

15 . The method of claim 13 , comprising:
determining, using the first device, whether a match can be identified at least to within the threshold level of confidence based on comparing the first frame of the RGB video content to one or more of the first frame of the IR video content and the data from the depth sensor.

16 . The method of claim 13 , comprising:
determining, using the first device, whether a match can be identified at least to within the threshold level of confidence based on the first frame of the RGB video content and both of: the first frame of the IR video content, the data from the depth sensor.

17 . The method of claim 13 , comprising:
prior to authenticating the RGB video content, identifying an indicator in at least one IR image frame; and responsive to identifying the indicator and responsive to determining that a match has been identified at least to within the threshold level of confidence, using the first device to authenticate the RGB video content for at least the first amount of time.

18 . The method of claim 17 , wherein the indicator is encrypted, and wherein the indicator denotes that the IR image frame is not fake.

19 . At least one computer readable storage medium (CRSM) that is not a transitory signal, the computer readable storage medium comprising instructions executable by at least one processor to:
access a first frame of red green blue (RGB) video content, the first frame of the RGB video cont

Assignees

• Lenovo Singapore Pte Ltd

Inventors

• Li Scott Wentao
• Stolbikov Igor
• Zugasti Alfredo

Classifications

• G06V10/143

  Sensing or illuminating at different wavelengths · CPC title

• G06V40/40 Primary

  Spoof detection, e.g. liveness detection · CPC title

• G06V10/147

  Details of sensors, e.g. sensor lenses (fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19) · 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

• H04N23/20

  for generating image signals from infrared radiation only · CPC title