Back to results
US 11,895,390 B2Granted
Stabilization of face in video
AssigneeGoPro, Inc.
InventorGuillaume Oules
Life of this patent
Estimating the term…
Abstract
Placement of a face depicted within a video may be determined. One or more stabilization options for the video may be obtained. Stabilization option(s) may include angle stabilization option, a position stabilization option, and/or a size stabilization option. The video may be stabilized based on the placement of the face and the stabilization option(s).
Claims20
A system for stabilizing videos, the system comprising:
- one or more physical processors configured by machine-readable instructions to:
- obtain video information defining a video having a progress length, the video including visual content, the visual content including depiction of an object;
- determine placement of the object within the visual content as the function of progress through the progress length based on one or more stable features of the object;
- and
- generate stabilized visual content based on the placement of the object within the visual content as the function of progress through the progress length, the stabilized visual content including stabilized depiction of the object, wherein generation of the stabilization visual content based on the placement of the object within the visual content as the function of progress through the progress length results in stabilization of the visual content based on the one or more stable features of the object included within the visual content rather than movement of an image capture device that captured the visual content.
2 more elements
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, video information defining a video having a progress length, the video including visual content, the visual content including depiction of a an object;
- determining, by the computing system, placement of the object within the visual content as the function of progress through the progress length based on one or more stable features of the object;
- and
- generating, by the computing system, stabilized visual content based on the placement of the object within the visual content as the function of progress through the progress length, the stabilized visual content including stabilized depiction of the object, wherein generating the stabilization visual content based on the placement of the object within the visual content as the function of progress through the progress length results in stabilization of the visual content based on the one or more stable features of the object included within the visual content rather than movement of an image capture device that captured the visual content.
1 more element
A system for stabilizing videos, the system comprising:
- one or more physical processors configured by machine-readable instructions to:
- obtain video information defining a video having a progress length, the video including visual content, the visual content including depiction of an object;
- determine placement of the object within the visual content as the function of progress through the progress length based on one or more stable features of the object, the one or more stable features of the object including one or more elements or one or more parts of the object that does not change over time or does not change as the object moves;
- and
- generate stabilized visual content based on the placement of the object within the visual content as the function of progress through the progress length, the stabilized visual content including stabilized depiction of the object, wherein generation of the stabilization visual content based on the placement of the object within the visual content as the function of progress through the progress length results in stabilization of the visual content based on the one or more stable features of the object included within the visual content rather than movement of an image capture device that captured the visual content.
2 more elements
Dependencies are inferred from the claim text.