Virtual field of view adjustment in live volumetric video
Video of a plurality of fields of view of a scene is captured, each field of view comprising data of the scene from a different vantage point. An excitement level is determined by analyzing a portion of the captured video. Using the excitement level, a time series of future excitement levels is forecast. Using the time series of future excitement levels, a virtual field of view path of the scene is forecast. An insert image is determined to be included in the virtual field of view path. Captured data from at least two video cameras in the plurality of video cameras is composited into a virtual field of view of the scene. A rendering of the insert image is inserted into the virtual field of view.
1 . A computer-implemented method comprising:
capturing, using a plurality of video cameras, video of a plurality of fields of view of a scene, each field of view comprising data of the scene from a different vantage point, the capturing resulting in captured video of the plurality of fields of view;
determining, by analyzing a portion of the captured video, an excitement level;
forecasting, using the excitement level, a time series of future excitement levels;
forecasting, using the time series of future excitement levels, a virtual field of view path of the scene;
determining that an insert image is included in the virtual field of view path;
compositing, into a virtual field of view of the scene, captured data from at least two video cameras in the plurality of video cameras; and
inserting, into the virtual field of view, a rendering of the insert image.
2 . The computer-implemented method of claim 1 , further comprising:
determining, by analyzing a portion of audio data of a vicinity of the scene, an audio-based excitement level corresponding to the scene; and
incorporating, into the excitement level, the audio-based excitement level.
3 . The computer-implemented method of claim 1 , further comprising:
identifying, by analyzing a portion of the captured video, an object within the scene; and
determining an object excitement level corresponding to the object.
4 . The computer-implemented method of claim 3 , further comprising:
determining, by analyzing a frame of the captured video, a frame excitement level; and
incorporating, into the object excitement level, the frame excitement level.
5 . The computer-implemented method of claim 3 , further comprising:
determining, by analyzing event data of an event occurring in the scene, an event excitement level; and
incorporating, into the object excitement level, the event excitement level.
6 . The computer-implemented method of claim 1 , further comprising:
removing, from the virtual field of view, a second object with a transparency level above a threshold transparency level, the transparency level set according to a second excitement level corresponding to the second object.
7 . The computer-implemented method of claim 1 , further comprising:
rendering, in the virtual field of view according to a transparency level of a third object, the third object, the transparency level of the third object set according to a third excitement level corresponding to the third object.
8 . The computer-implemented method of claim 1 , wherein the rendering is generated with a specified maximum angular offset.
9 . The computer-implemented method of claim 1 , wherein the rendering is generated with an angular offset determined according to a payment amount.
10 . The computer-implemented method of claim 1 , wherein the rendering is generated with an angular offset determined according to an amount of computing resources required to render the insert image at a specified angular offset.
11 . A computer program product for virtual field of view adjustment in volumetric video, the computer program product comprising:
one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the stored program instructions comprising:
program instructions to capture, using a plurality of video cameras, video of a plurality of fields of view of a scene, each field of view comprising data of the scene from a different vantage point, the capturing resulting in captured video of the plurality of fields of view;
program instructions to determine, by analyzing a portion of the captured video, an excitement level;
program instructions to forecast, using the excitement level, a time series of future excitement levels;
program instructions to forecast, using the time series of future excitement levels, a virtual field of view path of the scene;
program instructions to determine that an insert image is included in the virtual field of view path;
program instructions to composite, into a virtual field of view of the scene, captured data from at least two video cameras in the plurality of video cameras; and
program instructions to insert, into the virtual field of view, a rendering of the insert image.
12 . The computer program product of claim 11 , the stored program instructions further comprising:
program instructions to determine, by analyzing a portion of audio data of a vicinity of the scene, an audio-based excitement level corresponding to the scene; and
program instructions to incorporate, into the excitement level, the audio-based excitement level.
13 . The computer program product of claim 11 , the stored program instructions further comprising:
program instructions to identify, by analyzing a portion of the captured video, an object within the scene; and
program instructions to determine an object excitement level corresponding to the object.
14 . The computer program product of claim 13 , the stored program instructions further comprising:
program instructions to determine, by analyzing a frame of the captured video, a frame excitement level; and
program instructions to incorporate, into the object excitement level, the frame excitement level.
15 . The computer program product of claim 13 , the stored program instructions further comprising:
program instructions to determine, by analyzing event data of an event occurring in the scene, an event excitement level; and
program instructions to incorporate, into the object excitement level, the event excitement level.
16 . The computer program product of claim 11 , the stored program instructions further comprising:
program instructions to remove, from the virtual field of view, a second object with a transparency level above a threshold transparency level, the transparency level set according to a second excitement level corresponding to the second object.
17 . The computer program product of claim 11 , wherein the stored program instructions are stored in the at least one of the one or more storage media of a local data processing system, and wherein the stored program instructions are transferred over a network from a remote data processing system.
18 . The computer program product of claim 11 , wherein the stored program instructions are stored in the at least one of the one or more storage media of a server data processing system, and wherein the stored program instructions are downloaded over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system.
19 . The computer program product of claim 11 , wherein the computer program product is provided as a service in a cloud environment.
20 . A computer system comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage media, and program instructions stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:
program instructions to capture, using a plurality of video cameras, video of a plurality of fields of view of a scene, each field of view comprising data of the scene from a different vantage point, the capturing resulting in captured video of the plurality of fields of view;
program instructions to determine, by analyzing a portion of the captured video, an excitement level;
program instructions to forecast, using the excitement level, a time series of future excitement levels;
program instructions to forecast, using the time series of future excitement levels, a virtual field of view path of the scene;
program instructions to determine that an insert image is included in the virtual field of view path;
program instructions to composite, into a virtual field of view of the scene, captured data from at least two video cameras in the plurality of video cameras; and
program instructions to insert, into the virtual field of view, a rendering of the insert image.