Back to results
US 9,542,976 B2Granted
Synchronizing videos with frame-based metadata using video content
AssigneeGoogle Inc.
InventorsMichael Andrew Sipe, Michael Christian Nechyba
Life of this patent
Estimating the term…
Abstract
A transformed video and a source video may be synchronized according to implementations disclosed herein to provide tag information to the device receiving the transformed version of the video. A synchronization signal may be computed on the source video and the transformed video using a statistic such as mean pixel intensity. The synchronization signals computed for the transformed video and source video may be compared to determine a transformed video reference point location for the requested tag information. The requested tag information may be provided to the device receiving the transformed version of the video.
Claims28
A method, comprising:
- determining tag information for a plurality of entities in a video, wherein the tag information comprises an identity of each of the plurality of entities and a video entity reference location for each of the plurality of entities;
- determining a first synchronization signal for the video using a first statistic and a second statistic, each of the first statistic and the second statistic selected independently from the group consisting of:
- a mean pixel intensity, a mean color intensity, a mean color tone, a number of pixels of a particular intensity, a number of pixels of a particular color, and a centroid of a highest pixel intensity for a frame;
- providing a transformed version of the video;
- determining a second synchronization signal for the transformed version of the video using the second statistic;
- receiving a request for tag information for at least one of the plurality of entities in the transformed version of the video;
- comparing the first synchronization signal to the second synchronization signal to determine a transformed video reference point location for the requested tag information;
- and
- providing the requested tag information at the transformed video reference point location based on the comparison of the first synchronization signal to the second synchronization signal.
6 more elements
A system, comprising:
- a database for storing tag information for a plurality of entities in a video, wherein the tag information comprises an identity of each of the plurality of entities and a video entity reference location for each of the plurality of entities;
- and
- a processor communicatively coupled to the database and configured to:
- determine tag information for the plurality of entities in the video;
- determine a first synchronization signal for the video using a first statistic and a second statistic, each of the first statistic and the second statistic selected independently from the group consisting of:
- a mean pixel intensity, a mean color intensity, a mean color tone, a number of pixels of a particular intensity, a number of pixels of a particular color, and a centroid of a highest pixel intensity for a frame;
- provide a transformed version of the video;
- determine a second synchronization signal for the transformed version of the video using the second statistic;
- receive a request for tag information for at least one of the plurality of entities in the transformed version of the video;
- compare the first synchronization signal to the second synchronization signal to determine a transformed video reference point location for the requested tag information;
- and
- provide the requested tag information at the transformed video reference point location based on the comparison of the first synchronization signal to the second synchronization signal.
9 more elements
A method, comprising:
- determining tag information for a plurality of entities in a video, wherein the tag information comprises an identity of each of the plurality of entities and a video entity reference location for each of the plurality of entities;
- determining a first synchronization signal for the video using a first statistic and a second statistic, each of the first statistic and the second statistic selected independently from the group consisting of:
- a mean pixel intensity, a mean color intensity, a mean color tone, a number of pixels of a particular intensity, a number of pixels of a particular color, and a centroid of a highest pixel intensity for a frame;
- providing a transformed version of the video;
- receiving a second synchronization signal for the transformed version of the video using the second statistic;
- receiving a request for tag information for at least one of the plurality of entities in the transformed version of the video;
- comparing the first synchronization signal to the second synchronization signal to determine a transformed video reference point location for the requested tag information;
- and
- providing the requested tag information at the transformed video reference point location based on the comparison of the first synchronization signal to the second synchronization signal.
6 more elements
A system, comprising:
- a database for storing tag information for a plurality of entities in a video, wherein the tag information comprises an identity of each of the plurality of entities and a video entity reference location for each of the plurality of entities;
- and
- a processor communicatively coupled to the database and configured to:
- determine tag information for the plurality of entities in the video;
- determine a first synchronization signal for the video using a first statistic and a second statistic, each of the first statistic and the second statistic selected independently from the group consisting of:
- a mean pixel intensity, a mean color intensity, a mean color tone, a number of pixels of a particular intensity, a number of pixels of a particular color, and a centroid of a highest pixel intensity for a frame;
- provide a transformed version of the video;
- receive a second synchronization signal for the transformed version of the video using the second statistic;
- receive a request for tag information for at least one of the plurality of entities in the transformed version of the video;
- compare the first synchronization signal to the second synchronization signal to determine a transformed video reference point location for the requested tag information;
- and
- provide the requested tag information at the transformed video reference point location based on the comparison of the first synchronization signal to the second synchronization signal.
9 more elements
A method, comprising:
- receiving a first synchronization signal for a video that is based on a first statistic and a second statistic, each of the first statistic and the second statistic selected independently from the group consisting of:
- a mean pixel intensity, a mean color intensity, a mean color tone, a number of pixels of a particular intensity, a number of pixels of a particular color, and a centroid of a highest pixel intensity for a frame;
- receiving a transformed version of the video;
- determining a second synchronization signal for the transformed version of the video using the second statistic;
- comparing the first synchronization signal to the second synchronization signal to determine a transformed video reference point location;
- requesting tag information for at least one of a plurality of entities in the transformed version of the video based on the transformed video reference point location, wherein the tag information for the plurality of entities comprises an identity of each of the plurality of entities for the transformed video reference point location;
- and
- receiving the tag information for the at least one of the plurality of entities for the transformed video reference point location.
5 more elements
A system, comprising:
- a database for storing synchronization signal data;
- and
- a processor communicatively coupled to the database and configured to:
- receive a first synchronization signal for a video that is based on a first statistic and a second statistic, each of the first statistic and the second statistic selected independently from the group consisting of:
- a mean pixel intensity, a mean color intensity, a mean color tone, a number of pixels of a particular intensity, a number of pixels of a particular color, and a centroid of a highest pixel intensity for a frame;
- receive a transformed version of the video;
- determine a second synchronization signal for the transformed version of the video using the second statistic;
- compare the first synchronization signal to the second synchronization signal to determine a transformed video reference point location;
- request tag information for at least one of a plurality of entities in the transformed version of the video based on the transformed video reference point location, wherein the tag information for the plurality of entities comprises an identity of each of the plurality of entities for the transformed video reference point location;
- and
- receive the tag information for the at least one of the plurality of entities for the transformed video reference point location.
8 more elements
A method, comprising:
- determining tag information for a plurality of entities in a video, wherein the tag information comprises an identity of each of the plurality of entities and a video entity reference location for each of the plurality of entities;
- determining a first synchronization signal for the video using a statistic, the statistic selected independently from the group consisting of:
- a mean pixel intensity, a mean color intensity, a mean color tone, a number of pixels of a particular intensity, a number of pixels of a particular color, and a centroid of a highest pixel intensity for a frame;
- providing a transformed version of the video;
- determining a second synchronization signal for the transformed version of the video using the statistic;
- receiving a request for tag information for at least one of the plurality of entities in the transformed version of the video, the request including a query related to a selected portion of a video frame in the transformed version of the video;
- determining a corresponding selected portion of a video frame in the video;
- comparing the first synchronization signal to the second synchronization signal to determine a transformed video reference point location for the requested tag information;
- and
- providing the requested tag information at the transformed video reference point location based on the comparison of the first synchronization signal to the second synchronization signal, but excluding tag information for an entity that is not within the selected portion of the video frame in the transformed version of the video from being provided.
7 more elements
A system, comprising:
- a database for storing tag information for a plurality of entities in a video, wherein the tag information comprises an identity of each of the plurality of entities and a video entity reference location for each of the plurality of entities;
- and
- a processor communicatively coupled to the database and configured to:
- determine tag information for the plurality of entities in the video;
- determine a first synchronization signal for the video using a statistic, the statistic selected independently from the group consisting of:
- a mean pixel intensity, a mean color intensity, a mean color tone, a number of pixels of a particular intensity, a number of pixels of a particular color, and a centroid of a highest pixel intensity for a frame;
- provide a transformed version of the video;
- determine a second synchronization signal for the transformed version of the video using the statistic;
- receive a request for tag information for at least one of the plurality of entities in the transformed version of the video, the request including a query related to a selected portion of a video frame in the transformed version of the video;
- determine a corresponding selected portion of a video frame in the video;
- compare the first synchronization signal to the second synchronization signal to determine a transformed video reference point location for the requested tag information;
- and
- provide the requested tag information at the transformed video reference point location based on the comparison of the first synchronization signal to the second synchronization signal, but exclude tag information for an entity that is not within the selected portion of the video frame in the transformed version of the video from being provided.
10 more elements
A method, comprising:
- determining tag information for a plurality of entities in a video, wherein the tag information comprises an identity of each of the plurality of entities and a video entity reference location for each of the plurality of entities;
- determining a first synchronization signal for the video using a statistic, the statistic selected independently from the group consisting of:
- a mean pixel intensity, a mean color intensity, a mean color tone, a number of pixels of a particular intensity, a number of pixels of a particular color, and a centroid of a highest pixel intensity for a frame;
- providing a transformed version of the video;
- receiving a second synchronization signal for the transformed version of the video using the statistic;
- receiving a request for tag information for at least one of the plurality of entities in the transformed version of the video, the request including a query related to a selected portion of a video frame in the transformed version of the video;
- determining a corresponding selected portion of a video frame in the video;
- comparing the first synchronization signal to the second synchronization signal to determine a transformed video reference point location for the requested tag information;
- and
- providing the requested tag information at the transformed video reference point location based on the comparison of the first synchronization signal to the second synchronization signal, but excluding tag information for an entity that is not within the selected portion of the video frame in the transformed version of the video from being provided.
7 more elements
A system, comprising:
- a database for storing tag information for a plurality of entities in a video, wherein the tag information comprises an identity of each of the plurality of entities and a video entity reference location for each of the plurality of entities;
- and
- a processor communicatively coupled to the database and configured to:
- determine tag information for the plurality of entities in the video;
- determine a first synchronization signal for the video using a statistic, the statistic selected independently from the group consisting of:
- a mean pixel intensity, a mean color intensity, a mean color tone, a number of pixels of a particular intensity, a number of pixels of a particular color, and a centroid of a highest pixel intensity for a frame;
- provide a transformed version of the video;
- receive a second synchronization signal for the transformed version of the video using the statistic;
- receive a request for tag information for at least one of the plurality of entities in the transformed version of the video, the request including a query related to a selected portion of a video frame in the transformed version of the video;
- determine a corresponding selected portion of a video frame in the video;
- compare the first synchronization signal to the second synchronization signal to determine a transformed video reference point location for the requested tag information;
- and
- provide the requested tag information at the transformed video reference point location based on the comparison of the first synchronization signal to the second synchronization signal, but exclude tag information for an entity that is not within the selected portion of the video frame in the transformed version of the video from being provided.
10 more elements
Dependencies are inferred from the claim text.