Granted Patent B2

US 12,505,665 · App. 17/594,209 · Granted Dec 23, 2025

Inventors: Alex Olwal (Santa Cruz, CA); Kevin Balke (Sunnyvale, CA); Dmitrii Votintcev (Menlo Park, CA)

Assignee: GOOGLE LLC

G06V10/95G06V10/764G06V40/168H04N7/188

Abstract

Claims (66)

1 . A method comprising:

determining that a condition for motion of a wearable device achieves a threshold for stability based on sensor data from a motion sensor of the wearable device;

detecting, by a first model on the wearable device, whether or not an object of interest is included within a first image frame;

in response to the object of interest being detected in the first image frame and the condition achieving the threshold, transmitting the first image frame to a computing device;

receiving location data generated by a second model on the computing device, the location data identifying a location of the object of interest in the first image frame;

identifying an image region in a second image frame using the location data of the first image frame, the second image frame being subsequent to the first image frame; and

transmitting the image region to the computing device.

2 . The method of claim 1 , further comprising:

extracting the image region from the second image frame; and

generating a compressed image region from the image region, wherein the compressed image region is transmitted to the computing device.

3 . The method of claim 1 , wherein the object of interest includes facial features, wherein the method further comprises:

performing, by the second model, facial recognition using the image region of the second image frame.

4 . The method of claim 1 , further comprising:

receiving first image data from a first camera;

detecting whether the object of interest is included in the first image data; and

in response to the object of interest being detected in the first image data, activating a second camera to obtain second image data, the second image data having a resolution higher than the first image data, wherein the first image frame is selected from the second image data.

5 . The method of claim 4 , further comprising:

receiving, via a light condition sensor of the wearable device, light condition information, the light condition information indicating a level of light; and

activating the first camera based on the light condition information.

6 . The method of claim 1 , wherein the wearable device includes an extended reality device configured to be worn on a head of a user, and the computing device includes a mobile user device wirelessly connected to the extended reality device.

7 . The method of claim 1 , further comprising:

receiving classification data associated with the object of interest, the classification data being determined by the second model; and

rendering the classification data on the wearable device.

8 . The method of claim 7 , wherein the classification data is rendered at a location in a field of view of a user that corresponds to the object of interest.

9 . A non-transitory computer-readable medium storing executable instructions that when executed by at least one processor cause the at least one processor to execute operations, the operations comprising:

determining that a condition for motion of a wearable device achieves a threshold for stability based on sensor data from a motion sensor of the wearable device;

detecting, by a first model, whether or not an object of interest is included within a first image frame;

in response to the object of interest being detected in the first image frame and the condition achieving the threshold, transmitting the first image frame to a computing device;

receiving location data generated by a second model on the computing device, the location data identifying a location of the object of interest in the first image frame;

identifying an image region in a second image frame using the location data of the first image frame, the second image frame being subsequent to the first image frame; and

transmitting the image region to the computing device.

10 . The non-transitory computer-readable medium of claim 9 ,

wherein the operations further comprise:

selecting the image region from the second image frame; and

generating a compressed image region from the image region, wherein the compressed image region is transmitted to the computing device.

11 . The non-transitory computer-readable medium of claim 9 , wherein the object of interest includes a machine-readable representation of data, wherein the operations further comprise:

decoding, by the second model, the machine-readable representation of data from the image region.

12 . The non-transitory computer-readable medium of claim 9 , wherein the operations further comprise:

receiving first image data from a first camera;

detecting whether the object of interest is included in the first image data; and

in response to the object of interest being detected in the first image data, activating a second camera to obtain second image data, the second image data having a resolution higher than the first image data, wherein the first image frame is selected from the second image data.

13 . The non-transitory computer-readable medium of claim 12 , wherein the operations further comprise:

performing, by the second model, facial recognition using the image region of the second image frame.

14 . The non-transitory computer-readable medium of claim 12 , wherein the operations further comprise:

receiving light condition information from a light condition sensor of the wearable device, the light condition information indicating a level of ambient light; and

activating the first camera in response to the level of ambient light achieving a threshold level.

15 . A wearable device for distributed image recognition, the wearable device comprising:

at least one processor; and

a non-transitory computer-readable medium storing executable instructions that cause the at least one processor to:

determine that a condition for motion of a wearable device achieves a threshold for stability based on sensor data from a motion sensor of the wearable device;

detect whether or not an object of interest is included within a first image frame;

in response to the object of interest being detected in the first image frame and the condition achieving the threshold, transmit the first image frame to a computing device;

receive location data generated by a second model on the computing device, the location data identifying a location of the object of interest in the first image frame;

identify an image region in a second image frame using the location data of the first image frame, the second image frame being subsequent to the first image frame; and

transmit the image region to the computing device.

16 . The wearable device of claim 15 , wherein the executable instructions include instructions that cause the at least one processor to:

activate a first camera in response to a level of ambient light achieving a threshold condition;

receive first image data from the first camera;

detect whether the object of interest is included in the first image data; and

in response to the object of interest being detected in the first image data, activate a second camera to obtain second image data, the second image data having a resolution higher than the first image data, wherein the first image frame is selected from the second image data.

17 . The wearable device of claim 15 , wherein the executable instructions include instructions that cause the at least one processor to:

generate a compressed image region from the image region, wherein the compressed image region is transmitted to the computing device.

18 . The wearable device of claim 15 , wherein the executable instructions include instructions that cause the at least one processor to:

receive classification data associated with the object of interest, the classification data being determined by the second model; and

render the classification data at a location on a display of the wearable device that corresponds to a location of the object of interest.

19 . The wearable device of claim 15 , wherein the wearable device includes an extended reality device configured to be worn on a head of a user, the computing device includes a mobile user device wirelessly connected to the extended reality device.

Assignments (1)

Continuity (1)

References Cited (76)