AUTOMATIC GENERATION OF VIDEO FROM SPHERICAL CONTENT USING AUDIO/VISUAL ANALYSIS
First Claim
1. A method for generating output video content from spherical video content, the method performed by a computing system including one or more physical processors, the method comprising:
- accessing, by the computing system, a first spherical video comprising a first sequence of spherical video frames having a first spherical field of view;
accessing, by the computing system, a second spherical video comprising a second sequence of spherical video frames having a second spherical field of view;
processing, by the computing system, the first spherical video to identify a target feature of interest meeting one or more criteria;
determining, by the computing system, a first range of frames of the first spherical video including the target feature of interest;
determining, by the computing system, a second range of frames of the second spherical video including the target feature of interest;
determining, by the computing system, a first sequence of sub-frames from the first range of frames, the first sequence of sub-frames having a non-spherical field of view and including the target feature of interest;
determining, by the computing system, a second sequence of sub-frames from the second range of frames, the second sequence of sub-frames having a non-spherical field of view and including the target feature of interest;
generating, by the computing system, a first combined sequence of sub-frames including the target feature of interest, the first combined sequence comprising the first sequence of sub-frames and the second sequence of sub-frames; and
generating, by the computing system, a first portion of an output video including the first combined sequence of sub-frames.
4 Assignments
0 Petitions
Accused Products
Abstract
A spherical content capture system captures spherical video content. A spherical video sharing platform enables users to share the captured spherical content and enables users to access spherical content shared by other users. In one embodiment, captured metadata or video/audio processing is used to identify content relevant to a particular user based on time and location information. The platform can then generate an output video from one or more shared spherical content files relevant to the user. The output video may include a non-spherical reduced field of view such as those commonly associated with conventional camera systems. Particularly, relevant sub-frames having a reduced field of view may be extracted from each frame of spherical video to generate an output video that tracks a particular individual or object of interest.
15 Citations
20 Claims
-
1. A method for generating output video content from spherical video content, the method performed by a computing system including one or more physical processors, the method comprising:
-
accessing, by the computing system, a first spherical video comprising a first sequence of spherical video frames having a first spherical field of view; accessing, by the computing system, a second spherical video comprising a second sequence of spherical video frames having a second spherical field of view; processing, by the computing system, the first spherical video to identify a target feature of interest meeting one or more criteria; determining, by the computing system, a first range of frames of the first spherical video including the target feature of interest; determining, by the computing system, a second range of frames of the second spherical video including the target feature of interest; determining, by the computing system, a first sequence of sub-frames from the first range of frames, the first sequence of sub-frames having a non-spherical field of view and including the target feature of interest; determining, by the computing system, a second sequence of sub-frames from the second range of frames, the second sequence of sub-frames having a non-spherical field of view and including the target feature of interest; generating, by the computing system, a first combined sequence of sub-frames including the target feature of interest, the first combined sequence comprising the first sequence of sub-frames and the second sequence of sub-frames; and generating, by the computing system, a first portion of an output video including the first combined sequence of sub-frames. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A non-transitory computer-readable storage medium storing instructions for generating output video content from spherical video content, the instructions, when executed by one or more processors, causing the one or more processors to perform steps including:
-
accessing a first spherical video comprising a first sequence of spherical video frames having a first spherical field of view; accessing a second spherical video comprising a second sequence of spherical video frames having a second spherical field of view; processing the first spherical video to identify a target feature of interest meeting one or more criteria; determining a first range of frames of the first spherical video including the target feature of interest; determining a second range of frames of the second spherical video including the target feature of interest; determining a first sequence of sub-frames from the first range of frames, the first sequence of sub-frames having a non-spherical field of view and including the target feature of interest; determining a second sequence of sub-frames from the second range of frames, the second sequence of sub-frames having a non-spherical field of view and including the target feature of interest; generating a first combined sequence of sub-frames including the target feature of interest, the first combined sequence comprising the first sequence of sub-frames and the second sequence of sub-frames; and generating a first portion of an output video including the first combined sequence of sub-frames. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A system for generating output video content from spherical video content, the system comprising:
one or more physical processors configured by machine-readable instructions to; access a first spherical video comprising a first sequence of spherical video frames having a first spherical field of view; access a second spherical video comprising a second sequence of spherical video frames having a second spherical field of view; process the first spherical video to identify a target feature of interest meeting one or more criteria; determine a first range of frames of the first spherical video including the target feature of interest; determine a second range of frames of the second spherical video including the target feature of interest; determine a first sequence of sub-frames from the first range of frames, the first sequence of sub-frames having a non-spherical field of view and including the target feature of interest; determine a second sequence of sub-frames from the second range of frames, the second sequence of sub-frames having a non-spherical field of view and including the target feature of interest; generate a first combined sequence of sub-frames including the target feature of interest, the first combined sequence comprising the first sequence of sub-frames and the second sequence of sub-frames; and generate a first portion of an output video including the first combined sequence of sub-frames. - View Dependent Claims (16, 17, 18, 19, 20)
Specification