Systems and methods for framing videos based on image capture device motion

A system for framing videos, the system comprising:

• one or more physical processors configured by machine-readable instructions to:
• obtain video information defining a video, the video having a progress length, the video including visual content viewable as a function of progress through the progress length, the visual content having a field of view, the video captured by an image capture device;
• obtain gravity-direction information for the video, the gravity-direction information characterizing a direction of gravity with respect to the image capture device during the capture of the video;
• obtain north-direction information for the video, the north-direction information characterizing a direction of north with respect to the image capture device during the capture of the video;
• obtain orientation information for the video, the orientation information characterizing orientations of the image capture device during the capture of the video in an image capture device reference frame;
• obtain motion information for the video, the motion information characterizing a direction of motion of the image capture device during the capture of the video in an earth reference frame;
• merge the orientations of the image capture device during the capture of the video in the image capture device reference frame and the direction of motion of the image capture device during the capture of the video in the earth reference frame into a single reference frame based on the direction of gravity with respect to the image capture device during the capture of the video and the direction of north with respect to the image capture device during the capture of the video;
• position a viewing window within the field of view of the visual content based on the orientations of the image capture device during the capture of the video and the direction of motion of the image capture device during the capture of the video in the single reference frame;
• and
• present the visual content on an electronic display based on the viewing window,
• wherein the motion information characterizes the direction of motion of the image capture device during the capture of the video by including GPS locations of the image capture device during the capture of the video,
• wherein the viewing window is positioned within the field of view of the visual content to include an extent of the visual content in the direction of motion of the image capture device during the capture of the video,
• wherein the direction of motion of the image capture device at a given moment during the capture of the video is determined based on a given GPS location of the image capture device at the given moment and one or more future GPS locations of the image capture device at one or more future moments during the capture of the video,
• wherein the direction of motion of the image capture device at the given moment during the capture of the video is determined based on a combination of a short-term estimation of the direction of motion of the image capture device and a long-term estimation of the direction of motion of the image capture device, and
• wherein:
• the short-term estimation of the direction of motion of the image capture device is determined based on the given GPS location of the image capture device at the given moment and a first future GPS location of the image capture device at a first future moment;
• the long-term estimation of the direction of motion of the image capture device is determined based on the given GPS location of the image capture device at the given moment and a second future GPS location of the image capture device at a second future moment;
• and
• the second future GPS location is farther apart from the given GPS location than the first future GPS location, and
• wherein an impact of the long-term estimation of the direction of motion of the image capture device on the determination of the direction of motion of the image capture device increases with greater collinearity between the short-term estimation of the direction of motion of the image capture device and the long-term estimation of the direction of motion of the image capture device.

A method for framing videos, the method performed by a computing system including one or more processors, the method comprising:

• obtaining, by the computing system, video information defining a video, the video having a progress length, the video including visual content viewable as a function of progress through the progress length, the visual content having a field of view, the video captured by an image capture device;
• obtaining, by the computing system, gravity-direction information for the video, the gravity-direction information characterizing a direction of gravity with respect to the image capture device during the capture of the video;
• obtaining, by the computing system, north-direction information for the video, the north-direction information characterizing a direction of north with respect to the image capture device during the capture of the video;
• obtaining, by the computing system, orientation information for the video, the orientation information characterizing orientations of the image capture device during the capture of the video in an image capture device reference frame;
• obtaining, by the computing system, motion information for the video, the motion information characterizing a direction of motion of the image capture device during the capture of the video in an earth reference frame;
• merging, by the computing system, the orientations of the image capture device during the capture of the video in the image capture device reference frame and the direction of motion of the image capture device during the capture of the video in the earth reference frame into a single reference frame based on the direction of gravity with respect to the image capture device during the capture of the video and the direction of north with respect to the image capture device during the capture of the video;
• positioning, by the computing system, a viewing window within the field of view of the visual content based on the orientations of the image capture device during the capture of the video and the direction of motion of the image capture device during the capture of the video in the single reference frame;
• and
• presenting, by the computing system, the visual content on an electronic display based on the viewing window,
• wherein the motion information characterizes the direction of motion of the image capture device during the capture of the video by including GPS locations of the image capture device during the capture of the video,
• wherein the viewing window is positioned within the field of view of the visual content to include an extent of the visual content in the direction of motion of the image capture device during the capture of the video,
• wherein the direction of motion of the image capture device at a given moment during the capture of the video is determined based on a given GPS location of the image capture device at the given moment and one or more future GPS locations of the image capture device at one or more future moments during the capture of the video,
• wherein the direction of motion of the image capture device at the given moment during the capture of the video is determined based on a combination of a short-term estimation of the direction of motion of the image capture device and a long-term estimation of the direction of motion of the image capture device,
• wherein:
• the short-term estimation of the direction of motion of the image capture device is determined based on the given GPS location of the image capture device at the given moment and a first future GPS location of the image capture device at a first future moment;
• the long-term estimation of the direction of motion of the image capture device is determined based on the given GPS location of the image capture device at the given moment and a second future GPS location of the image capture device at a second future moment;
• and
• the second future GPS location is farther apart from the given GPS location than the first future GPS location;
• and
• wherein an impact of the long-term estimation of the direction of motion of the image capture device on the determination of the direction of motion of the image capture device increases with greater collinearity between the short-term estimation of the direction of motion of the image capture device and the long-term estimation of the direction of motion of the image capture device.