Adaptive image processing for augmented reality device

Patent metadata

Field	Value
Publication number	US-12462491-B2
Application number	US-202318118906-A
Country	US
Kind code	B2
Filing date	Mar 8, 2023
Priority date	Mar 8, 2023
Publication date	Nov 4, 2025
Grant date	Nov 4, 2025

Abstract

Examples describe adaptive image processing for an augmented reality (AR) device. An input image is captured by a camera of the AR device, and a region of interest of the input image is determined. The region of interest is associated with an object that is being tracked using an object tracking system. A crop-and-scale order of an image processing operation directed at the region of interest is determined for the input image. One or more object tracking parameters may be used to determine the crop-and-scale order. The crop-and-scale order is dynamically adjustable between a first order and a second order. An output image is generated from the input image by performing the image processing operation according to the determined crop-and-scale order for the particular input image. The output image can be accessed by the object tracking system to track the object.

First claim

What is claimed is:

1 . A method comprising:
accessing a first input image captured using at least one camera of an augmented reality (AR) device; determining a region of interest of the first input image, the region of interest of the first input image including an object that is being tracked using an object tracking system; determining, for the first input image and based on one or more object tracking parameters, a crop-and-scale order of an image processing operation directed at the region of interest of the first input image, the crop-and-scale order being dynamically adjustable between a first order and a second order, and the one or more object tracking parameters comprising at least one of object tracking status data, an object motion prediction, an object position relative to the region of interest, an AR device motion prediction, an AR device frame bending estimation, one or more camera-display transformation values, or a margin padding value; generating, via performing of the image processing operation, a first output image from the first input image; accessing a second input image captured using the at least one camera, the second input image depicting the object and captured subsequent to capturing of the first input image; automatically adjusting, for the second input image and based on the one or more object tracking parameters, the crop-and-scale order of the image processing operation such that the crop-and-scale order for the second input image differs from the crop-and-scale order for the first input image; generating, via performing of the image processing operation according to the crop-and-scale order for the second input image, a second output image from the second input image; and accessing, by the object tracking system, the first output image and the second output image to track the object.

2 . The method of claim 1 , wherein the one or more object tracking parameters comprise object tracking data for a previous input image captured prior to the first input image using the at least one camera of the AR device, the crop-and-scale order for the first input image being automatically determined based at least in part on the object tracking data for the previous input image.

3 . The method of claim 2 , further comprising:
capturing, using the at least one camera of the AR device, a plurality of images defining a sequence of frames, the sequence of frames including the first input image, the second input image, and the previous input image, and the previous input image immediately preceding the first input image in the sequence of frames.

4 . The method of claim 1 , wherein the first output image is defined by a cropped and scaled image obtained from within the first input image using the image processing operation, the cropped and scaled image having a predefined size, and the first input image having a first size that differs from the predefined size.

5 . The method of claim 4 , wherein the object tracking system uses a sequence of cropped and scaled images of the predefined size to track the object.

6 . The method of claim 1 , wherein the determining the region of interest of the first input image comprises calculating a display overlapping region of the first input image, the display overlapping region being a region of overlap between the first input image and a display area defined by a display of the AR device.

7 . The method of claim 6 , wherein the determining the region of interest of the first input image further comprises determining the region of interest within the display overlapping region based at least partially on the one or more object tracking parameters.

8 . The method of claim 1 , wherein the first order is a crop-then-scale order in which cropping is automatically performed prior to scaling to obtain an output image of a predefined size, and wherein the second order is a scale-then-crop order in which scaling is automatically performed prior to cropping to obtain an output image of the predefined size.

9 . The method of claim 8 , wherein, for the first input image, the crop-then-scale order comprises cropping the region of interest from the first input image to obtain a cropped region of interest, and then scaling the cropped region of interest to the predefined size to obtain the first output image.

10 . The method of claim 8 , wherein, for the first input image, the scale-then-crop order comprises scaling the first input image such that the region of interest of the first input image is scaled to the predefined size, and then cropping the scaled region of interest from the scaled first input image to obtain the first output image.

11 . The method of claim 8 , wherein the first order is stored as a default order for the image processing operation in a storage component associated with the AR device, the crop-and-scale order being dynamically and automatically adjustable to the second order based on the one or more object tracking parameters.

12 . The method of claim 1 , further comprising:
determining a region of interest of the second input image.

13 . The method of claim 1 , further comprising:
capturing, using the at least one camera of the AR device, a plurality of images defining a sequence of frames, the frames including the first input image and the second input image, and the first input image immediately preceding the second input image in the sequence of frames.

14 . The method of claim 1 , wherein the adjusting the crop-and-scale order for the second input image comprises automatically adjusting the crop-and-scale order based on values for the one or more object tracking parameters as determined for the first input image.

15 . The method of claim 1 , wherein the object tracking system comprises an object tracking machine learning model that tracks the object in a three-dimensional space.

16 . The method of claim 1 , wherein the AR device is a head-wearable apparatus.

17 . The method of claim 16 , wherein the AR device comprises wearable computing glasses.

18 . A computing apparatus comprising:
at least one processor; and memory storing instructions that, when executed by the processor, configure the apparatus to perform operations comprising:
accessing a first input image captured using at least one camera of an augmented reality (AR) device;
determining a region of interest of the first input image, the region of interest of the first input image including an object that is being tracked using an object tracking system;
determining, for the first input image and based on one or more object tracking parameters, a crop-and-scale order of an image processing operation directed at the region of interest of the first input image, the crop-and-scale order being dynamically adjustable between a first order and a second order, and the one or more object tracking parameters comprising at least one of object tracking status data, an object motion prediction, an object position relative to the region of interest, an AR device motion prediction, an AR device frame bending estimation, one or more camera-display transformation values, or a margin padding value;
generating, via performing of the image processing operation, a first output image from the first input image;
accessing a second input image captured using the at least one camera, the second input image depicting the object and captured subsequent to capturing of the first input image;
automatically adjusting, for the second input image and based on the one or more object tracking parameters, the crop-and-sca

Assignees

• Snap Inc

Inventors

• Muttenthaler Thomas
• Zhou Kai

Classifications

• G06T3/40

  Scaling of whole images or parts thereof, e.g. expanding or contracting · CPC title

• G02B2027/0178

  Eyeglass type (eyeglass details G02C) · CPC title

• G02B27/0172

  characterised by optical features · CPC title

• G06V2201/07

  Target detection · CPC title

• G06V10/25

  Determination of region of interest [ROI] or a volume of interest [VOI] · CPC title