Identifying one or more events in content
AssigneeComcast Cable Communications, LLC
InventorsErik Schwartz, Jan Neumann, Hans Sayyadi, Stefan Deichmann
Life of this patent
Estimating the term…
Abstract
According to some aspects, methods and systems may include receiving, by a computing device, metadata identifying an event occurring in a video program, and determining an expected motion of objects in the identified event. The methods and systems may further include analyzing motion energy in the video program to identify video frames in which the event occurs, and storing information identifying the video frames in which the event occurs.
Claims20
A method comprising:
- receiving, by a computing device, metadata indicative of a time for a beginning of an event occurring in a video program and a time for an ending of the event;
- determining, based on the metadata and based on a plurality of video frames associated with the video program:
- a first video frame, from the plurality of video frames, comprising a first displayed time before the time for the beginning of the event;
- and
- a second video frame, from the plurality of video frames, comprising a second displayed time after the time for the ending of the event;
- selecting a portion of the video program, the portion comprising the first video frame, the second video frame, and video frames between the first video frame and the second video frame;
- determining an expected motion energy of objects associated with the event;
- determining, based on a comparison of motion energy of objects in the selected portion of the video program with the expected motion energy, one or more video frames, within the selected portion, in which the event occurs;
- and
- storing information indicating the one or more video frames in which the event occurs.
An apparatus comprising:
- one or more processors;
- and
- memory storing instructions that, when executed by the one or more processors, cause the apparatus to:
- receive metadata indicative of a time for a beginning of an event occurring in a video program and a time for an ending of the event;
- determine, based on the metadata and based on a plurality of video frames associated with the video program:
- a first video frame, from the plurality of video frames, comprising a first displayed time before the time for the beginning of the event;
- and
- a second video frame, from the plurality of video frames, comprising a second displayed time after the time for the ending of the event;
- select a portion of the video program, the portion comprising the first video frame, the second video frame, and video frames between the first video frame and the second video frame;
- determine an expected motion energy of objects associated with the event;
- determine, based on a comparison of motion energy of objects in the selected portion of the video program with the expected motion energy, one or more video frames, within the selected portion, in which the event occurs;
- and
- store information indicating the one or more video frames in which the event occurs.
A non-transitory computer-readable medium storing instructions that, when executed, cause:
- receiving, by a computing device, metadata indicative of a time for a beginning of an event occurring in a video program and a time for an ending of the event;
- determining, based on the metadata and based on a plurality of video frames associated with the video program:
- a first video frame, from the plurality of video frames, comprising a first displayed time before the time for the beginning of the event;
- and
- a second video frame, from the plurality of video frames, comprising a second displayed time after the time for the ending of the event;
- selecting a portion of the video program, the portion comprising the first video frame, the second video frame, and video frames between the first video frame and the second video frame;
- determining an expected motion energy of objects associated with the event;
- determining, based on a comparison of motion energy of objects in the selected portion of the video program with the expected motion energy, one or more video frames, within the selected portion, in which the event occurs;
- and
- storing information indicating the one or more video frames in which the event occurs.
Dependencies are inferred from the claim text.