IP Library Granted Patent US 10,559,083
Granted Patent B2
US 10,559,083 · App. 16/231,001 · Granted Feb 11, 2020

Systems and methods for horizon identification in an image

Inventor: Vincent Garcia (Issy-les-Moulineaux, FR)
Assignee: GoPro, Inc.
G06T7/13G06K9/00664G06K9/4642G06T7/70G06T7/90G06K9/4652
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,559,083
App. No.
16/231,001
Granted
Feb 11, 2020
Kind
B2
Abstract

Systems and method of identifying a horizon depicted in an image are presented herein. Information defining an image may be obtained. The image may include visual content comprising an array of pixels. The array may include pixel rows. Parameter values for a set of pixel parameters of individual pixels of the image may be determined. Individual average parameter values of the individual pixel parameters of the pixels in the individual pixel rows may be determined. Based on the average parameter values a pixel row may be identified as depicting a horizon in the image.

Claims (31)

1. A system configured to identify a horizon in an image, the system comprising:

one or more physical processors configured by machine-readable instructions to:

obtain information defining an image, the image including visual content comprising an array of pixels, the information defining individual colors for individual pixels in the array, the array including pixel rows;

determine parameter values for a set of pixel parameters of individual pixels of the image;

determine secondary parameter values for the set of pixel parameters of individual pixel rows of the image based on corresponding parameter values of the pixels in the individual pixel rows, the secondary parameter values determined based on one or more of an average, a weight average, a median, a mode, and/or an entropy of the corresponding parameter values;

identify one or more pixel rows of the image as depicting the horizon in the image based on the secondary parameter values; and

effectuate an image effect on the image based on the identification of the one or more pixel rows of the image as depicting the horizon in the image.

2. The system of claim 1 , wherein the set of pixel parameters includes one or more of a first color parameter, a second color parameter, a third color parameter, a fourth color parameter, a first image gradient parameter, a second image gradient parameter, or a gradient magnitude parameter.

3. The system of claim 2 , wherein the first color parameter corresponds to a first color component of the individual colors of the pixels in the array, the second color parameter corresponds to a second color component of the individual colors of the pixels in the array, the third color parameter corresponds to a third color component of the individual colors of the pixels in the array, the fourth color parameter corresponds to a fourth color component of the individual colors of the pixels in the array, the first image gradient parameter corresponds to an image gradient at the individual pixels in the array in a first direction, the second image gradient parameter corresponds to an image gradient at the individual pixels in the array in a second direction, and the gradient magnitude parameter corresponds to a magnitude of the image gradient at the individual pixels in the array.

4. The system of claim 3 , wherein the first color component, second color component, third color component, and fourth color component correspond to individual colors channels within an RGBY color space, and wherein parameter values of the first color component, second color component, third color component, and fourth color component are luminous intensities associated with the individual color channels.

5. The system of claim 1 , wherein the one or more physical processors are further configured by machine-readable instructions to determine an image gradient of the image.

6. The system of claim 1 , wherein the image effect includes an overlaying of text at or near the one or more pixel rows, a scrolling of text across the one or more pixel rows, a scrolling of text above or below the one or more pixel rows, a fading in or a fading out at the one or more pixel rows, or an adjustment of crop position based on the one or more pixel rows.

7. The system of claim 1 , wherein the image depicts a scene including scene content, wherein the one or more pixel rows are identified as depicting the horizon in the image based on the scene content at the one or more pixel rows including a visual depiction of the horizon.

8. The system of claim 1 , wherein the image depicts a scene including scene content, wherein the one or more pixel rows are identified as depicting the horizon in the image irrespective of the scene content including a visual depiction of the horizon.

9. The system of claim 1 , wherein identifying the one or more pixel rows as depicting the horizon comprises identifying, based on the secondary parameter values of the individual pixel parameters of the pixels in the individual pixel rows, a set of pixel rows and selecting the one or more pixel rows from the set of pixel rows.

10. The system of claim 1 , wherein identifying the one or more pixel rows as depicting the horizon in the image comprises generating a matrix, the matrix having rows corresponding to individual pixel rows and columns corresponding to individual secondary parameter values of individual pixel parameters in the set of pixel parameters.

11. A method of identifying a horizon in an image, the method being implemented in a computer system comprising one or more physical processors and non-transitory electronic storage media storing machine-readable instructions, the method comprising:

obtaining information defining an image, the image including visual content comprising an array of pixels, the information defining individual colors for individual pixels in the array, the array including pixel rows;

determining parameter values for a set of pixel parameters of individual pixels of the image;

determining secondary parameter values for the set of pixel parameters of individual pixel rows of the image based on corresponding parameter values of the pixels in the individual pixel rows, the secondary parameter values determined based on one or more of an average, a weight average, a median, a mode, and/or an entropy of the corresponding parameter values;

identifying one or more pixel rows of the image as depicting the horizon in the image based on the secondary parameter values; and

effectuating an image effect on the image based on the identification of the one or more pixel rows of the image as depicting the horizon in the image.

12. The method of claim 11 , wherein the set of pixel parameters includes one or more of a first color parameter, a second color parameter, a third color parameter, a fourth color parameter, a first image gradient parameter, a second image gradient parameter, or a gradient magnitude parameter.

13. The method of claim 12 , wherein the first color parameter corresponds to a first color component of the individual colors of the pixels in the array, the second color parameter corresponds to a second color component of the individual colors of the pixels in the array, the third color parameter corresponds to a third color component of the individual colors of the pixels in the array, the fourth color parameter corresponds to a fourth color component of the individual colors of the pixels in the array, the first image gradient parameter corresponds to an image gradient at the individual pixels in the array in a first direction, the second image gradient parameter corresponds to an image gradient at the individual pixels in the array in a second direction, and the gradient magnitude parameter corresponds to a magnitude of the image gradient at the individual pixels in the array.

14. The method of claim 13 , wherein the first color component, second color component, third color component, and fourth color component correspond to individual colors channels within an RGBY color space, and wherein parameter values of the first color component, second color component, third color component, and fourth color component are luminous intensities associated with the individual color channels.

15. The method of claim 11 , further comprising determining an image gradient of the image.

16. The method of claim 11 , wherein the image effect includes an overlaying of text at or near the one or more pixel rows, a scrolling of text across the one or more pixel rows, a scrolling of text above or below the one or more pixel rows, a fading in or a fading out at the one or more pixel rows, or an adjustment of crop position based on the one or more pixel rows.

17. The method of claim 11 , wherein the image depicts a scene including scene content, wherein the one or more pixels rows are identified as depicting the horizon in the image based on the scene content at the one or more pixel rows including a visual depiction of the horizon.

18. The method of claim 11 , wherein the image depicts a scene including scene content, wherein the one or more pixel rows are identified as depicting the horizon in the image irrespective of the scene content including a visual depiction of the horizon.

19. The method of claim 11 , wherein identifying the one or more pixel rows as depicting the horizon comprises identifying, based on the secondary parameter values of the individual pixel parameters of the pixels in the individual pixel rows, a set of pixel rows, and selecting the one or more pixel rows from the set of pixel rows.

20. The method of claim 11 , wherein identifying the one or more pixel rows as depicting the horizon in the image comprises generating a matrix, the matrix having rows corresponding to individual pixel rows and columns corresponding to individual secondary parameter values of individual pixel parameters in the set of pixel parameters.

Assignments (6)
SECURITY INTEREST Recorded Aug 4, 2025
From: GOPRO, INC.
To: FARALLON CAPITAL MANAGEMENT, L.L.C., AS AGENT
Reel/Frame 072340/0676 →
SECURITY INTEREST Recorded Aug 4, 2025
From: GOPRO, INC.
To: WELLS FARGO BANK, NATIONAL ASSOCIATION, AS AGENT
Reel/Frame 072358/0001 →
RELEASE OF PATENT SECURITY INTEREST Recorded Jan 25, 2021
From: JPMORGAN CHASE BANK, N.A., AS ADMINISTRATIVE AGENT
To: GOPRO, INC.
Reel/Frame 055106/0434 →
SECURITY INTEREST Recorded Oct 19, 2020
From: GOPRO, INC.
To: JPMORGAN CHASE BANK, N.A., AS ADMINISTRATIVE AGENT
Reel/Frame 054113/0594 →
SECURITY INTEREST Recorded Mar 5, 2019
From: GOPRO, INC.
To: JPMORGAN CHASE BANK, N.A., AS ADMINISTRATIVE AGENT
Reel/Frame 048508/0728 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 21, 2018
From: GARCIA, VINCENT
To: GOPRO, INC.
Reel/Frame 047846/0801 →
Continuity (2)
Continuation 15344412 · Nov 4, 2016
Related Publication 20190147596A1 · May 16, 2019