Systems and methods for stabilizing videos

Patent metadata

Field	Value
Publication number	US-11979662-B2
Application number	US-202318161004-A
Country	US
Kind code	B2
Filing date	Jan 27, 2023
Priority date	Sep 19, 2018
Publication date	May 7, 2024
Grant date	May 7, 2024

Abstract

Visual content is captured by an image capture device during a capture duration. The image capture devices experiences motion during the capture duration. The intentionality of the motion of the image capture device is determined based on angular acceleration of the image capture device during the capture duration. A punchout of the visual content is determined based on the intentionality of the motion of the image capture device. The punchout of the visual content is used to generate stabilized visual content.

First claim

What is claimed is:

1. A system for stabilizing videos, the system comprising:
one or more physical processors configured by machine-readable instructions to:
obtain visual information, the visual information defining visual content captured by an image capture device during a capture duration, the visual content having a field of view;
obtain angular acceleration information, the angular acceleration information characterizing angular accelerations of the image capture device at different moments within the capture duration;
determine intentionality of motion of the image capture device as a function of progress through the capture duration based on comparison of the angular accelerations of the image capture device with a fully intentional angular acceleration threshold value and a fully unintentional angular acceleration threshold value, wherein the intentionality of motion of the image capture device is determined as being fully unintentional based on the angular accelerations of the image capture device being greater than the fully unintentional angular acceleration threshold value, as being fully intentional based on the angular accelerations of the image capture device being smaller than a fully intentional angular acceleration threshold value, and as being intermediately intentional based on the angular accelerations of the image capture device being between the fully intentional angular acceleration threshold value and the fully unintentional angular acceleration threshold value;
determine placement of a viewing window within the field of view of the visual content as the function of progress through the capture duration based on the intentionality of motion of the image capture device, a centering parameter, an inertia parameter, and a deviation parameter, the viewing window defining one or more extents of the visual content, the centering parameter controlling an extent to which the viewing window is moved towards a center of the visual content when the viewing window is not located at the center of the visual content, the inertia parameter controlling an extent to which speed of the viewing window changes across the capture duration, and the deviation parameter controlling an extent to which the viewing window is allowed to move away from the center of the visual content, wherein the deviation parameter controlling the extent to which the viewing window is allowed to move away from the center of the visual content includes the deviation parameter defining maximum angular distances that the viewing window is allowed to deviate from the center of the visual content; and
generate stabilized visual content based on the viewing window, the stabilized visual content including a punchout of the one or more extents of the visual content within the viewing window.

2. The system of claim 1 , wherein the one or more physical processors and a display are carried by the image capture device, and the stabilized visual content is presented on the display as a live preview of video capture during the capture duration.

3. The system of claim 2 , wherein the image capture device performs a different stabilization of the visual content to generate more stabilized visual content for generation of a video, the more stabilized visual content providing a more stable view than the live preview of the video capture presented during the capture duration.

4. The system of claim 1 , wherein the centering parameter controlling the extent to which the viewing window is moved towards the center of the visual content when the viewing window is not located at the center of the visual content includes the centering parameter controlling speed with which an uncentered viewing window is moved towards the center of the visual content.

5. The system of claim 4 , wherein:
impact of the centering parameter on the placement of the viewing window is determined based on the intentionality of motion of the image capture device;
based on the intentionality of motion of the image capture device being fully intentional, the impact of the centering parameter on the placement of the viewing window is increased to increase the speed with which the uncentered viewing window is moved towards the center of the visual content; and
based on the intentionality of motion of the image capture device being fully unintentional, the impact of the centering parameter on the placement of the viewing window is eliminated.

6. The system of claim 1 , wherein the inertia parameter controlling the extent to which the speed of the viewing window changes within the capture duration includes the inertia parameter limiting an amount by which the speed of the viewing window is allowed to be changed.

7. The system of claim 6 , wherein:
impact of the inertia parameter on the placement of the viewing window is determined based on the intentionality of motion of the image capture device;
based on the intentionality of motion of the image capture device being fully intentional, the impact of the inertia parameter on the placement of the viewing window is decreased to allow for less change in the speed with which the viewing window is moved; and
based on the intentionality of motion of the image capture device being fully unintentional, the impact of the inertia parameter on the placement of the viewing window is increased to allow for greater change in the speed with which the viewing window is moved.

8. The system of claim 1 , wherein:
deviation limit on the placement of the viewing window imposed by the deviation parameter is determined based on the intentionality of motion of the image capture device;
based on the intentionality of motion of the image capture device being fully intentional, the deviation limit on the placement of the viewing window imposed by the deviation parameter is decreased to allow less deviation of the viewing window from the center of the visual content; and
based on the intentionality of motion of the image capture device being fully unintentional, the deviation limit on the placement of the viewing window imposed by the deviation parameter is increased to allow greater deviation of the viewing window from the center of the visual content.

9. A method for stabilizing videos, the method performed by a computing system including one or more processors, the method comprising:
obtaining, by the computing system, visual information, the visual information defining visual content captured by an image capture device during a capture duration, the visual content having a field of view;
obtaining, by the computing system, angular acceleration information, the angular acceleration information characterizing angular accelerations of the image capture device at different moments within the capture duration;
determining, by the computing system, intentionality of motion of the image capture device as a function of progress through the capture duration based on comparison of the angular accelerations of the image capture device with a fully intentional angular acceleration threshold value and a fully unintentional angular acceleration threshold value, wherein the intentionality of motion of the image capture device is determined as being fully unintentional based on the angular accelerations of the image capture device being greater than the fully unintentional angular acceleration threshold value, as being fully intentional based on the angular accelerations of the image capture device being smaller than a fully intentional angular acceleration threshold value, and as being intermediately intentional based on the angular accelerations of the image capture device being between the fully intentional angular acceleration threshold value and the fully unintentional angular acceleratio

Assignees

• Gopro Inc

Inventors

• Douady Cesar
• Derbanne Thomas
• Karpushin Maxim

Classifications

• H04N23/685 Primary

  performed by mechanical compensation · CPC title

• H04N5/144

  Movement detection (for video coding H04N19/503; analysis of motion in general G06T7/20) · CPC title

• H04N23/51

  Housings · CPC title

• H04N23/54

  Mounting of pick-up tubes, electronic image sensors, deviation or focusing coils · CPC title

• H04N23/55

  Optical parts specially adapted for electronic image sensors; Mounting thereof · CPC title