AUTOMATIC GENERATION OF VIDEO FROM SPHERICAL CONTENT USING LOCATION-BASED METADATA

摘要

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.

主权项

1. A method for generating an output video from spherical video content, the method comprising:
storing, by a video server, a first spherical video having first spherical video content and first video metadata including location data pertaining to a location of a first camera capturing the first spherical video content and timing data pertaining to a time of capture of the first spherical video content; receiving user metadata representing a target path, the target path comprising a sequence of time-stamped locations corresponding to a target; determining by the video server, based on the user metadata and the first video metadata, a first matching portion of the first spherical video, the first matching portion captured when the first camera was within a threshold vicinity of the target; determining a sequence of sub-frames by selecting, for each of a plurality of frames of the first matching portion of the first spherical video, a sub-frame having content relevant to the target path, each of the sequence of sub-frames comprising a non-spherical field of view; combining the sequence of sub-frames to generate a first portion of the output video relevant to the target; and outputting the output video.