Systems and methods for stabilizing videos
Images with an optical field of view are captured by an image capture device. An observed trajectory of the image capture device reflects the positions of the image capture device at different moments may be determined. A capture trajectory of the image capture device reflects virtual positions of the image capture device from which video content may be generated. The capture trajectory is determined based on a subsequent portion of the observed trajectory such that a portion of the capture trajectory corresponding to a portion of the observed trajectory is determined based on a subsequent portion of the observed trajectory. Orientations of punch-outs for the images are determined based on the capture trajectory. Video content is generated based on visual content of the images within the punch-outs.
1. An image capture device that stabilizes videos, the image capture device comprising:
a housing;
an optical element carried by the housing and configured to guide light to an image sensor;
the image sensor carried by the housing and configured to generate an image output signal based on light that becomes incident thereon during a capture duration, the image output signal conveying image information that defines images with a field of view;
a position sensor carried by the housing and configured to generate a position output signal based on positions of the housing during the capture duration, the position output signal conveying position information that characterizes rotational positions of the housing at different moments within the capture duration; and
one or more physical processors configured by machine-readable instructions to:
determine an observed trajectory of the housing during the capture duration based on the position information, the observed trajectory reflecting the rotational positions of the housing at the different moments within the capture duration;
determine a capture trajectory of the housing based on a look ahead of the observed trajectory, the capture trajectory reflecting actual and/or virtual positions of the housing from which orientations of a capture field of view with respect to the field of view of the images are determined, the look head of the observed trajectory including use of a subsequent portion of the observed trajectory to determine a preceding portion of the capture trajectory such that a portion of the capture trajectory corresponding to a first moment within the capture duration is determined based on a portion of the observed trajectory corresponding to a second moment subsequent to the first moment within the capture duration, wherein the capture trajectory is determined to include a path that minimizes a combination of rotational velocity and rotational acceleration of the housing, the combination of the rotational velocity and the rotational acceleration of the housing weighing the rotational velocity and the rotational acceleration equally or differently;
determine the orientations of the capture field of view with respect to the field of view of the images based on the capture trajectory of the housing; and
generate stabilized video content based on a punch-out of visual content of the images within the capture field of view.
2. The image capture device of claim 1 , wherein the position information further characterizes translational positions of the housing at the different moments within the capture duration.
3. The image capture device of claim 1 , wherein the position sensor includes a gyroscope, an accelerometer, and/or an inertial measurement unit.
4. The image capture device of claim 1 , wherein the capture trajectory has less jitters in the rotational positions of the housing than the observed trajectory.
5. The image capture device of claim 4 , wherein high frequency changes in the rotational positions of the housing of the observed trajectory are removed from the capture trajectory.
6. The image capture device of claim 1 , wherein the combination of the rotational velocity and the rotational acceleration of the housing is minimized while respecting a set of constraints.
7. The image capture device of claim 6 , wherein the set of constraints includes a margin constraint determined based on a difference between the optical field of view and the capture field of view.
8. The image capture device of claim 7 , wherein the set of constraints includes a trajectory constraint determined based on the subsequent portion of the observed trajectory.
9. The image capture device of claim 8 , wherein the set of constraints includes a target constraint determined based on positions of a target in the images.
10. The image capture device of claim 1 , wherein the one or more physical processors are, to generate the stabilized video content based on the punch-out of the visual content of the images within the capture field of view, further configured by machine-readable instructions to crop the visual content of the images within the capture field of view.
11. A method for stabilizing videos, the method performed by an image capture device including a housing and one or more processors, the housing carrying an optical element, an image sensor, and a position sensor, the optical element configured to guide light to the image sensor, the method comprising:
generating, by the image sensor, an image output signal based on light that becomes incident thereon during a capture duration, the image output signal conveying image information that defines images with a field of view;
generating, by the position sensor, a position output signal based on positions of the housing during the capture duration, the position output signal conveying position information that characterizes rotational positions of the housing at different moments within the capture duration;
determining, by the one or more processors, an observed trajectory of the housing during the capture duration based on the position information, the observed trajectory reflecting the rotational positions of the housing at the different moments within the capture duration;
determining, by the one or more processors, a capture trajectory of the housing based on a look ahead of the observed trajectory, the capture trajectory reflecting actual and/or virtual positions of the housing from which orientations of a capture field of view with respect to the field of view of the images are determined, the look head of the observed trajectory including use of a subsequent portion of the observed trajectory to determine a preceding portion of the capture trajectory such that a portion of the capture trajectory corresponding to a first moment within the capture duration is determined based on a portion of the observed trajectory corresponding to a second moment subsequent to the first moment within the capture duration, wherein the capture trajectory is determined to include a path that minimizes a combination of rotational velocity and rotational acceleration of the housing, the combination of the rotational velocity and the rotational acceleration of the housing weighing the rotational velocity and the rotational acceleration equally or differently;
determining, by the one or more processors, the orientations of the capture field of view with respect to the field of view of the images based on the capture trajectory of the housing; and
generating, by the one or more processors, stabilized video content based on a punch-out of visual content of the images within the capture field of view.
12. The method of claim 11 , wherein the position information further characterizes translational positions of the housing at the different moments within the capture duration.
13. The method of claim 11 , wherein the position sensor includes a gyroscope, an accelerometer, and/or an inertial measurement unit.
14. The method of claim 11 , wherein the capture trajectory has less jitters in the rotational positions of the housing than the observed trajectory.
15. The method of claim 14 , wherein high frequency changes in the rotational positions of the housing of the observed trajectory are removed from the capture trajectory.
16. The method of claim 11 , wherein the combination of the rotational velocity and the rotational acceleration of the housing is minimized while respecting a set of constraints.
17. The method of claim 16 , wherein the set of constraints includes a margin constraint determined based on a difference between the optical field of view and the capture field of view.
18. The method of claim 17 , wherein the set of constraints includes a trajectory constraint determined based on the subsequent portion of the observed trajectory.
19. The method of claim 18 , wherein the set of constraints includes a target constraint determined based on positions of a target in the images.
20. The method of claim 11 , wherein generating the stabilized video content based on the punch-out of the visual content of the images within the capture field of view includes cropping the visual content of the images within the capture field of view.