Video Stitching System and Method
AssigneeGoogle Inc.
InventorsVincent MO, David Cohen, Aravind Krishnaswamy
Life of this patent
Estimating the term…
Abstract
A method and computing system for receiving a first video file containing a first plurality of video frames. A second video file containing a second plurality of video frames is received. The video files are processed to identify at least one non-graphical temporal alignment object included in each of the video files. The video files are temporally aligned using the at least one non-graphical temporal alignment object to produce temporally-aligned video files.
Claims21
1-20. (canceled)
A computer-implemented method comprising:
- receiving a first video file containing a first plurality of video frames from a first device having a first frame rate;
- receiving a second video file containing a second plurality of video frames from a second device having a second frame rate;
- processing the video files to identify at least one non-graphical temporal alignment object included in each of the video files;
- temporally aligning the video files using the at least one non-graphical temporal alignment object to produce temporally-aligned video files;
- and
- combining the temporally-aligned video files to generate a consolidated output file having one or more of a higher resolution and a longer duration than each of the video files, wherein combining the video files to generate a consolidated output file includes one or more of:
- combining one or more of the first plurality of video frames included within the first video file and one or more of the second plurality of video frames included within the second video file to generate one or more higher resolution video frames for inclusion within the consolidated output file, and
- appending at least a portion of the second video file to at least a portion of the first video file to generate the consolidated output file having a longer duration than each of the video files.
A computer-implemented method comprising:
- receiving a first video file containing a first plurality of video frames from a first device having a first frame rate;
- receiving a second video file containing a second plurality of video frames from a second device having a second frame rate that is higher than the first frame rate;
- down-converting the frame rate of the second video file to the frame rate of the first video file;
- processing the video files to identify at least one non-graphical temporal alignment object included in each of the video files;
- temporally aligning the video files using the at least one non-graphical temporal alignment object to produce temporally-aligned video files;
- and
- combining the temporally-aligned video files to generate a consolidated output file.
A computing system including a processor and memory configured to perform operations comprising:
- receiving a first video file containing a first plurality of video frames from a first device having a first frame rate;
- receiving a second video file containing a second plurality of video frames from a second device having a second frame rate that is higher than the first frame rate;
- down-converting the frame rate of the second video file to the frame rate of the first video file;
- processing the video files to identify at least one non-graphical temporal alignment object included in each of the video files;
- temporally aligning the video files using the at least one non-graphical temporal alignment object to produce temporally-aligned video files;
- and
- combining the temporally-aligned video files to generate a consolidated output file.
Dependencies are inferred from the claim text.