US 11,606,532 B2Granted

Video reformatting system

AssigneeSnap Inc.

InventorsJoel Brandt, Giles Goodwin, Jared Iwata, Ian Wehrman

Life of this patent

Estimating the term…

Loading patent…

Abstract

Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program and a method for receiving, by one or more processors, a video comprising one or more shots in a first aspect ratio; detecting a first shot of the one or more shots, the first shot comprising a sequence of frames; and identifying an object that appears throughout a continuous portion of frames of the sequence of frames in the first shot. A visual presentation of the object in the first shot is automatically modified and a modified video comprising the one or more shots in a second aspect ratio is generated based on the automatically modified visual presentation of the object in the first shot.

Claims13

Dependent claims

A method comprising:

receiving, by one or more processors, a video comprising one or more shots in a first aspect ratio;
detecting one or more of objects that appear throughout a continuous sequence of frames in a first shot of the video;
determining a number of objects that are included in the one or more of objects;
in response to determining that the number of objects corresponds to one object, aligning the one or more objects within a vertical window corresponding to a second aspect ratio, the vertical window placed on top of the one or more objects, centering the one or more objects in the vertical window;
in response to determining that the number of objects corresponds to two objects and that the one or more objects are static, performing operations comprising:
generating two copies of the first shot;
inserting a first copy of the two copies of the first shot in a top section of the vertical window and a second copy of the two copies in a bottom section of the vertical window;
determining a first object and a second object of the one or more objects;
centering the first object of the one or more objects in the top section of the vertical window;
centering the second object of the one or more objects in the bottom section of the vertical window;
and
cropping other content in the first shot that is not shown in the top section or the bottom section;
in response to determining that the number of objects corresponds to three objects, performing operations comprising:
generating reduced size frames of the first shot that include the one or more objects;
positioning the reduced size frames in the top section of the vertical window;
determining a first object of the one or more objects focusing the bottom;
section of the vertical window on the first object of the one or more objects in the frames;
cropping out other content of the frames of the first shot outside of the bottom section of the vertical window;
and
reducing a size of the first object to fit within the bottom section of the vertical window.

17 more elements

A system comprising:

a processor configured to perform operations comprising:
receiving a video comprising one or more shots in a first aspect ratio;
detecting one or more objects in a first shot of the video;
determining a number of objects that are included in the one or more objects;
in response to determining that the number of objects corresponds to one object, aligning the one or more objects within a vertical window corresponding to a second aspect ratio, the vertical window placed on top of the one or more objects, centering the one or more objects in the vertical window;
in response to determining that the number of objects corresponds to two objects and that the one or more objects are static, performing operations comprising:
generating two copies of the first shot;
inserting a first copy of the two copies of the first shot in a top section of a vertical window and a second copy of the two copies in a bottom section of the vertical window;
determining a first object and a second object of the one or more objects;
centering the first object of the one or more objects in the top section of the vertical window;
centering the second object of the one or more objects in the bottom section of the vertical window;
and
cropping other content in the first shot that is not shown in the top section or the bottom section;
and
in response to determining that the number of objects corresponds to three objects and that the one or more objects are static, performing:
generating a reduced size version of frames of the first shot that include the one or more objects;
positioning the reduced size version of the frames in a top section of a vertical window;
focusing a bottom section of the vertical window on an object of the one or more objects in the frames;
cropping out other content of the frames outside of the bottom section of the vertical window;
and
reducing a size of the object to fit within the bottom section of the vertical window.

18 more elements

A non-transitory machine-readable storage medium that includes instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

detecting one or more objects in a first shot of a video;
determining a number of objects that are included in the one or more objects;
in response to determining that the number of objects corresponds to one object, aligning the one or more objects within a vertical window corresponding to a second aspect ratio, the vertical window placed on top of the one or more objects, centering the one or more objects in the vertical window;
in response to determining that the number of objects corresponds to two objects, performing operations comprising:
generating two copies of the first shot;
inserting a first copy of the two copies of the first shot in a top section of the vertical window and a second copy of the two copies of the first shot in a bottom section of the vertical window;
determining a first object and a second object of the one or more objects;
centering the first object of the one or more objects in the top section of the vertical window;
centering the second object of the one or more objects in the bottom section of the vertical window;
and
cropping other content in the first shot that is not shown in the top section or the bottom section;
and
in response to determining that the number of objects corresponds to three objects, performing operations comprising:
generating a reduced size version of frames of the first shot that include the one or more objects;
positioning the reduced size version of the frames in the top section of the vertical window;
determining a first object of the one or more objects;
focusing the bottom section of the vertical window on the first object of the one or more objects in the frames;
cropping out other content of the frames outside of the bottom section of the vertical window;
and
reducing a size of the first object to fit within the bottom section of the vertical window.

17 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/247,173Filed 2 Dec 2020 · continuation
Priority: 27 Dec 2018
Published: US 2021/0092323 A125 Mar 2021
Granted: 14 Mar 2023
Term ends: Not estimatedThe source records don’t support an estimate.

Classification14 codes

H04N 7/0117
Conversion of standards , e.g. involving analogue television standards or digital television standards processed at pixel level: involving…
G11B 27/031
Editing, e.g. varying the order of information signals recorded on, or reproduced from, record carriers: electronic editing of digitised analogue…
G11B 27/28
By using information detectable on the record carrier: by using information signals recorded by the same method as the main recording
G11B 27/3081
On the same track as the main recording: used signal is a video-frame or a video-field