# US 12,002,168 B2 · Low latency hand-tracking in augmented reality systems

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,002,168 B2
- Document ID: US12002168B2
- Status: Granted
- Kind: B2
- Application number: 17/844,541
- Filed: 2022-06-20
- Published: 2024-03-21
- Granted: 2024-06-04
- Earliest claimed: 2022-06-20
- Assignees: Snap Inc.
- Applicants: Snap Inc.
- Inventors: Jan Bajana; Bernhard Jung; Daniel Wagner
- Web page: https://patentgrep.com/patent/US12002168B2

## CPC

- G06F 3/011: {Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00)}
- G06T 19/006: {Mixed reality (object pose determination, tracking or camera calibration for mixed reality G06T7/00)}
- G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51)
- G06T 15/005: {General purpose rendering architectures}
- G06V 20/20: in augmented reality scenes
- G06V 40/28: {Recognition of hand or arm movements, e.g. recognition of deaf sign language (static hand signs G06V40/113)}
- G06T 2200/28: involving image processing hardware
- G06T 2207/30196: Human being; Person
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method for reducing motion-to-photon latency for hand tracking is described. In one aspect, a method includes accessing a first frame from a camera of an Augmented Reality (AR) device, tracking a first image of a hand in the first frame, rendering virtual content based on the tracking of the first image of the hand in the first frame, accessing a second frame from the camera before the rendering of the virtual content is completed, the second frame immediately following the first frame, tracking, using the computer vision engine of the AR device, a second image of the hand in the second frame, generating an annotation based on tracking the second image of the hand in the second frame, forming an annotated virtual content based on the annotation and the virtual content, and displaying the annotated virtual content in a display of the AR device.

## Claims

### Claim 1

A method comprising:
accessing a first frame from a camera of an Augmented Reality (AR) device;
tracking, using a computer vision engine of the AR device, a first image of a hand in the first frame;
rendering, using a render engine of a Graphical Processing Unit (GPU) of the AR device, virtual content based on the tracking of the first image of the hand in the first frame, wherein the camera and the render engine operate at a same frequency;
accessing a second frame from the camera before the rendering of the virtual content is completed, the second frame immediately following the first frame;
tracking, using the computer vision engine of the AR device, a second image of the hand in the second frame;
generating an annotation based on tracking the second image of the hand in the second frame;
forming an annotated virtual content based on the annotation and the virtual content; and
displaying the annotated virtual content in a display of the AR device.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
adjusting a timing of the camera and a timing of the rendering engine such that tracking the second image of the hand in the second frame finishes before a display controller sends the annotated virtual content to the display.

### Claim 3 (depends on 1)

The method of claim 1, wherein tracking the second image of the hand in the second frame is completed before the render engine completes the rendering of the virtual content.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
aligning, using a timing controller, a timing of the camera with a timing of the render engine based on the computer vision engine tracking the second image of the hand in the second frame being completed before the render engine completes the rendering of the virtual content.

### Claim 5 (depends on 1)

The method of claim 1, wherein accessing the second frame is during the rendering of the virtual content.

### Claim 6 (depends on 1)

The method of claim 1, wherein tracking the second image of the hand in the second frame is completed before the rendering of the virtual content is completed.

### Claim 7 (depends on 1)

The method of claim 1, wherein forming the annotated virtual content comprises:
drawing fingers tracking annotations on the virtual content.

### Claim 8

An Augmented Reality (AR) device comprising:
a camera;
a display;
a Graphical Processing Unit (GPU);
a processor; and
a memory storing instructions that, when executed by the processor, configure the AR device to:
access a first frame from the camera;
track, using a computer vision engine of the AR device, a first image of a hand in the first frame;
render, using a render engine of the GPU, virtual content based on the tracking of the first image of the hand in the first frame, wherein the camera and the render engine operate at a same frequency;
access a second frame from the camera before the rendering of the virtual content is completed, the second frame immediately following the first frame;
track, using the computer vision engine of the AR device, a second image of the hand in the second frame;
generate an annotation based on tracking the second image of the hand in the second frame;
form an annotated virtual content based on the annotation and the virtual content; and
display the annotated virtual content in the display.

### Claim 9 (depends on 8)

The AR device of claim 8, wherein the instructions further configure the AR device to:
adjust a timing of the camera and a timing of the rendering engine such that tracking the second image of the hand in the second frame finishes before a display controller sends the annotated virtual content to the display.

### Claim 10 (depends on 8)

The AR device of claim 8, wherein tracking the second image of the hand in the second frame is completed before the render engine completes the rendering of the virtual content.

### Claim 11 (depends on 8)

The AR device of claim 8, wherein the instructions further configure the AR device to:
align, using a timing controller, a timing of the camera with a timing of the render engine based on the computer vision engine tracking the second image of the hand in the second frame being completed before the render engine completes the rendering of the virtual content.

### Claim 12 (depends on 8)

The AR device of claim 8, wherein accessing the second frame is during the rendering of the virtual content.

### Claim 13 (depends on 8)

The AR device of claim 8, wherein tracking the second image of the hand in the second frame is completed immediately before the rendering of the virtual content is completed.

### Claim 14 (depends on 8)

The AR device of claim 8, wherein forming the annotated virtual content comprises:
drawing fingers tracking annotations on the virtual content.

### Claim 15

A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to:
access a first frame from a camera of an Augmented Reality (AR) device;
track, using a computer vision engine of the AR device, a first image of a hand in the first frame;
render, using a render engine of a Graphical Processing Unit (GPU) of the AR device, virtual content based on the tracking of the first image of the hand in the first frame;
access a second frame from the camera before the rendering of the virtual content is completed, the second frame immediately following the first frame, wherein the camera and the render engine operate at a same frequency;
track, using the computer vision engine of the AR device, a second image of the hand in the second frame;
generate an annotation based on tracking the second image of the hand in the second frame;
form an annotated virtual content based on the annotation and the virtual content; and
display the annotated virtual content in a display of the AR device.

### Claim 16 (depends on 15)

The computer-readable storage medium of claim 15, further comprising:
adjusting a timing of the camera and a timing of the rendering engine such that tracking the second image of the hand in the second frame finishes before a display controller sends the annotated virtual content to the display.

### Claim 17 (depends on 15)

The computer-readable storage medium of claim 15, wherein tracking the second image of the hand in the second frame is completed before the render engine completes the rendering of the virtual content.

### Claim 18 (depends on 15)

The computer-readable storage medium of claim 15, wherein the instructions further configure the computer to:
align, using a timing controller, a timing of the camera with a timing of the render engine based on the computer vision engine tracking the second image of the hand in the second frame being completed before the render engine completes the rendering of the virtual content.

### Claim 19 (depends on 15)

The computer-readable storage medium of claim 15, wherein accessing the second frame is during the rendering of the virtual content.

### Claim 20 (depends on 15)

The computer-readable storage medium of claim 15, wherein tracking the second image of the hand in the second frame is completed before the rendering of the virtual content is completed.