Granted Patent B2

US 12,333,761 · App. 18/609,845 · Granted Jun 17, 2025

Inventor: Kai Zhou (Wiener Neudorf, AT)

Assignee: Snap Inc.

G06T7/80G06T7/73G06T2200/04G06T2200/24

Abstract

Claims (76)

1. A method comprising:

generating a first image with a camera of a visual tracking system;

in response to generating the first image, detecting that a temperature of the camera exceeds a factory calibration temperature threshold of the camera;

in response to detecting that the temperature of the camera exceeds the factory calibration temperature threshold, generating a second image with the camera being aimed at a peripheral region of the first image; and

determining intrinsic parameters of the camera based on one or more features in a central region of the first image and in the peripheral region of the second image, and one or more projected features in the peripheral region of the second image based on factory intrinsic calibration parameters of the visual tracking system.

2. The method of claim 1 , further comprising:

matching pairs of one or more feature points in the peripheral region of the second image with corresponding one or more projected feature points in the peripheral region of the second image,

wherein determining the intrinsic parameters of the camera is based on the matching pairs of the one or more feature points in the peripheral region of the second image with the corresponding one or more projected feature points in the peripheral region of the second image.

3. The method of claim 1 , further comprising:

measuring the temperature of the camera after the camera is turned on, the temperature of the camera being higher than the factory calibration temperature threshold;

identifying the intrinsic parameters of the camera based on the temperature of the camera and a temperature profile of the camera; and

applying the intrinsic parameters to the one or more projected features of the camera.

4. The method of claim 1 , further comprising:

storing the intrinsic parameters of the camera in a storage device of the visual tracking system, wherein the visual tracking system includes a visual-inertial simultaneous localization and mapping system that is used to track the one or more features.

5. The method of claim 1 , further comprising:

identifying the one or more features that are located in the central region of the first image; and

detecting the one or more features in the peripheral region of the second image, the peripheral region of the second image corresponding to the central region of the first image.

6. The method of claim 1 , further comprising:

identifying the one or more features that are located in the central region of the first image;

detecting the one or more features in the peripheral region of the second image, the peripheral region of the second image corresponding to the central region of the first image; and

calculating the one or more projected features in the peripheral region of the second image based on the factory intrinsic calibration parameters of the visual tracking system.

7. The method of claim 6 , further comprising:

matching pairs of the one or more features in the peripheral region of the second image with corresponding one or more projected features in the peripheral region of the second image,

wherein determining the intrinsic parameters of the camera is based on the matching pairs of the one or more features in the peripheral region of the second image with the corresponding one or more projected features in the peripheral region of the second image.

8. The method of claim 7 , further comprising:

filtering the matching pairs by:

identifying a direction of a pair of one or more detected features and the one or more projected features, the direction indicating a radially outward direction from the one or more detected features to the one or more projected features,

wherein determining the intrinsic parameters of the camera is further based on the filtered matching pairs.

9. The method of claim 7 , further comprising:

filtering the matching pairs by:

limiting a pixel changing range between one or more detected features and corresponding one or more projected features of a matching pair,

wherein determining the intrinsic parameters of the camera is further based on the filtered matching pairs.

10. The method of claim 7 , further comprising:

filtering the matching pairs by:

limiting a pixel shifting based on a radial location of the one or more detected features, the pixel shifting being greater for a detected feature point that is further from the central region,

wherein determining the intrinsic parameters of the camera is further based on the filtered matching pairs.

11. The method of claim 7 , further comprising:

identifying a relationship between the intrinsic parameters and the temperature of the camera based on the matching pairs; and

forming a temperature profile of the camera based on the relationship.

12. The method of claim 1 , further comprising:

in response to detecting that the temperature of the camera exceeds the factory calibration temperature threshold, generating a graphical user interface element that instructs a user of the visual tracking system to move the visual tracking system towards the peripheral region of the first image.

13. The method of claim 12 , further comprising:

displaying the graphical user interface element in a display of the visual tracking system, the graphical user interface element comprising a vector that indicates a direction and a magnitude of displacement of the visual tracking system, wherein the direction points to the peripheral region of the first image, wherein the magnitude of displacement is based on an angular rotation between the central region of the first image and the peripheral region of the first image.

14. The method of claim 1 , further comprising:

in response to detecting that the temperature of the camera exceeds the factory calibration temperature threshold, identifying a number of feature points corresponding to a 3D location exceeds a feature point threshold; and

generating an instruction to direct the visual tracking system so that the 3D location is located in the peripheral region of the second image.

15. The method of claim 1 , further comprising:

identifying a plurality of locations in the peripheral region of the first image, the plurality of locations being dispersed throughout a perimeter of the first image;

displaying a graphical user interface element with instructions to sequentially move the visual tracking system so that one or more detected features are sequentially visible at each of the plurality of locations;

tracking, using the visual tracking system, the one or more detected features at each of the plurality of locations and a corresponding pose of the visual tracking system at each of the plurality of locations;

calculating the one or more projected features at each of the plurality of locations using the factory intrinsic calibration parameters of the visual tracking system;

matching pairs of the one or more detected features at each of the plurality of locations with the corresponding one or more projected features at each of the plurality of locations; and

determining the intrinsic parameters of the camera based on the matching pairs of the one or more detected features and the one or more projected features at the plurality of locations.

16. A visual tracking system comprising:

a camera;

a processor; and

a memory storing instructions that, when executed by the processor, configure the visual tracking system to perform operations comprising:

generating a first image with the camera;

in response to generating the first image, detecting that a temperature of the camera exceeds a factory calibration temperature threshold of the camera;

in response to detecting that the temperature of the camera exceeds the factory calibration temperature threshold, generating a second image with the camera being aimed at a peripheral region of the first image; and

determining intrinsic parameters of the camera based on one or more features in a central region of the first image and in the peripheral region of the second image, and one or more projected features in the peripheral region of the second image based on factory intrinsic calibration parameters of the visual tracking system.

17. The visual tracking system of claim 16 , wherein the operations further comprise:

matching pairs of one or more feature points in the peripheral region of the second image with corresponding one or more projected feature points in the peripheral region of the second image,

wherein determining the intrinsic parameters of the camera is based on the matching pairs of the one or more feature points in the peripheral region of the second image with the corresponding one or more projected feature points in the peripheral region of the second image.

18. The visual tracking system of claim 16 , wherein the operations further comprise:

identifying one or more feature points that are located in the central region of the first image; and

detecting the one or more feature points in the peripheral region of the second image, the peripheral region of the second image corresponding to the central region of the first image.

19. The visual tracking system of claim 16 , wherein the operations further comprise:

identifying one or more feature points that are located in the central region of the first image;

detecting one or more feature points in the peripheral region of the second image, the peripheral region of the second image corresponding to the central region of the first image; and

calculating one or more projected feature points in the peripheral region of the second image based on the factory intrinsic calibration parameters of the visual tracking system.

20. A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to perform operations comprising:

generating a first image with a camera of a visual tracking system;

in response to generating the first image, detecting that a temperature of the camera exceeds a factory calibration temperature threshold of the camera;

in response to detecting that the temperature of the camera exceeds the factory calibration temperature threshold, generating a second image with the camera being aimed at a peripheral region of the first image; and

determining intrinsic parameters of the camera based on one or more features in a central region of the first image and in the peripheral region of the second image, and one or more projected features in the peripheral region of the second image based on factory intrinsic calibration parameters of the visual tracking system.

Assignments (1)

Continuity (2)

References Cited (22)

Cited By (1)

US 12,579,690