Systems and methods for stabilizing videos

Patent metadata

Field	Value
Publication number	US-2023171496-A1
Application number	US-202318161004-A
Country	US
Kind code	A1
Filing date	Jan 27, 2023
Priority date	Sep 19, 2018
Publication date	Jun 1, 2023
Grant date	—

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; and
stabilize the visual content 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, the fully intentional angular acceleration threshold value being smaller than the fully unintentional angular acceleration threshold value.

2 . The system of claim 1 , wherein portions of the capture duration of the visual content are stabilized differently based on the angular accelerations of the image capture device for the portions being smaller than the fully intentional angular acceleration threshold value, being greater than the fully unintentional angular acceleration threshold value, or being between the fully intentional angular acceleration threshold value and the fully unintentional angular acceleration threshold value.

3 . The system of claim 2 , wherein the one or more physical processors and a display are carried by the image capture device, and the visual content stabilized based on the comparison of the angular accelerations of the image capture device with the fully intentional angular acceleration threshold value and the fully unintentional angular acceleration threshold value is presented on the display as a preview of a video during the capture duration.

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

5 . The system of claim 1 , wherein:
values of a stabilizer state variable are determined based on the angular accelerations of the image capture device; and the comparison of the angular accelerations of the image capture device with the fully intentional angular acceleration threshold value and the fully unintentional angular acceleration threshold value includes comparison of the values of the stabilizer state variable with a maximum value and a minimum value.

6 . The system of claim 5 , wherein the stabilization of the visual content based on the comparison of the angular accelerations of the image capture device with the fully intentional angular acceleration threshold value and the fully unintentional angular acceleration threshold value includes determination of a viewing window for the visual content as the function of progress through the capture duration based on the values of the stabilizer state variable, the viewing window defining one or more extents of the visual content for the stabilization of the visual content.

7 . The system of claim 6 , wherein placement of the viewing window for the visual content with respect to the field of view of the visual content is determined based on a centering parameter that moves the viewing window towards a center of the field of view, wherein an impact of the centering parameter on the placement of the viewing window is determined based on the values of the stabilizer state variable.

8 . The system of claim 6 , wherein placement of the viewing window for the visual content with respect to the field of view of the visual content is determined based on an inertia parameter that maintains a portion of speed of movement of the viewing window, wherein an impact of the inertia parameter on the placement of the viewing window is determined based on the values of the stabilizer state variable.

9 . The system of claim 6 , wherein placement of the viewing window for the visual content with respect to the field of view of the visual content is determined based on a deviation parameter that limits deviation of the viewing window from a center of the field of view.

10 . 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; and stabilizing, by the computing system, the visual content based on the 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, the fully intentional angular acceleration threshold value being smaller than the fully unintentional angular acceleration threshold value.

11 . The method of claim 10 , wherein portions of the capture duration of the visual content are stabilized differently based on the angular accelerations of the image capture device for the portions being smaller than the fully intentional angular acceleration threshold value, being greater than the fully unintentional angular acceleration threshold value, or being between the fully intentional angular acceleration threshold value and the fully unintentional angular acceleration threshold value.

12 . The method of claim 11 , wherein the one or more physical processors and a display are carried by the image capture device, and the visual content stabilized based on the comparison of the angular accelerations of the image capture device with the fully intentional angular acceleration threshold value and the fully unintentional angular acceleration threshold value is presented on the display as a preview of a video during the capture duration.

13 . The method of claim 12 , wherein the image capture device performs a different stabilization of the visual content to generate more stabilized visual content for the video, the more stabilized visual content providing a more stable view than the preview of the video presented during the capture duration.

14 . The method of claim 10 , wherein:
values of a stabilizer state variable are determined based on the angular accelerations of the image capture device; and the comparison of the angular accelerations of the image capture device with the fully intentional angular acceleration threshold value and the fully unintentional angular acceleration threshold value includes comparison of the values of the stabilizer state variable with a maximum value and a minimum value.

15 . The method of claim 14 , wherein stabilizing the visual content based on the comparison of the angular accelerations of the image capture device with the fully intentional angular acceleration threshold value and the fully unintentional angular acceleration threshold value includes determining a viewing window for the visual content as the function of progress through the capture duration based on the values of the stabilizer state variable, the viewing window defining one or more extents of the visual content for the stabilization of the visual content.

16 . The method of cla

Assignees

• Gopro Inc

Inventors

• Douady Cesar
• Derbanne Thomas
• Karpushin Maxim

Classifications

• H04N23/683 Primary

  performed by a processor, e.g. controlling the readout of an image memory · CPC title

• H04N23/685 Primary

  performed by mechanical compensation · CPC title

• H04N23/631

  Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters · CPC title

• H04N23/6812

  based on additional sensors, e.g. acceleration sensors · CPC title

• H04N23/55

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