Generation of event video frames for content

Patent metadata

Field	Value
Publication number	US-9646387-B2
Application number	US-201414514602-A
Country	US
Kind code	B2
Filing date	Oct 15, 2014
Priority date	Oct 15, 2014
Publication date	May 9, 2017
Grant date	May 9, 2017

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.

First claim

What is claimed is:

1. A method comprising:
determining, by a computing device, an approximate time range associated with an event occurring within a content item;
determining a range of video frames from the content item and corresponding to the approximate time range;
determining an expected motion of objects corresponding to the event;
determining, based on motion of objects in the range of video frames and based on the expected motion of the objects corresponding to the event, one or more video frames comprising the event;
storing information indicating the one or more video frames comprising the event;
receiving, by the computing device and from a user device, a request to view the event; and
in response to the request, and based on the information indicating the one or more video frames comprising the event, causing playback of the event.

2. The method of claim 1 , wherein the determining the one or more video frames further comprises:
determining a first set of frames, from the range of video frames, having motion energy satisfying a threshold energy level; and
determining a second set of frames, from the range of video frames, having motion energy that does not satisfy the threshold energy level.

3. The method of claim 2 , further comprising:
determining the first set of frames as comprising the event; and
determining the second set of frames as an ending of the event.

4. The method of claim 1 , wherein the determining the one or more video frames further comprises:
dividing one or more frames of the range of video frames into a first section and a second section; and
comparing a first motion energy vector of the first section with a second motion energy vector of the second section.

5. The method of claim 1 , wherein the determining the expected motion of the objects is further based on:
receiving information indicating a type of the content item; and
determining one or more object motion patterns associated with the type of the content item.

6. The method of claim 1 , further comprising:
determining one or more camera angles associated with the range of video frames; and
determining the one or more video frames based on the one or more camera angles and an audio associated with the content item.

7. A method comprising:
determining, by a computing device and based on an approximate time at which an event occurs within a content item, a set of video frames associated with the content item;
determining a profile, for the content item, that indicates a first expected camera angle and a second expected camera angle corresponding to the event;
determining a first frame, from the set of video frames, as a start of the event based on correlating a first camera angle of the first frame with the first expected camera angle;
determining a second frame, from the set of video frames, as an end of the event based on correlating a second camera angle of the second frame with the second expected camera angle;
receiving, by the computing device and from a user device, a request to view the event; and
causing playback of the event in response to the request and based on the first frame and the second frame.

8. The method of claim 7 , wherein the determining the set of video frames is further based on analyzing motion energy in one or more frames of the content item in response to determining that the event is a sporting event, and wherein the analyzing the motion energy is performed according to rules associated with the sporting event.

9. The method of claim 8 further comprising:
determining one or more rules associated with the sporting event; and
analyzing on-screen graphics associated with the one or frames based on the one or more rules.

10. The method of claim 7 , wherein the determining the set of video frames that are to be processed is further based on determining that the approximate time corresponds to a clock time displayed within one or more frames of the content item.

11. The method of claim 7 , wherein the determining the set of video frames is further based on:
analyzing audio characteristics associated with the event; and
using optical character recognition to analyze on-screen graphics associated with one or more frames of the content item.

12. A method comprising:
receiving, by a computing device, metadata indicating an approximate clock time for an event occurring in a content item;
determining one or more video frames, comprising the event, by using optical character recognition to compare the approximate clock time with one or more displayed clock times associated with a plurality of frames for the content item;
storing information indicating the one or more video frames comprising the event;
receiving, by the computing device and from a user device, a request to view the event; and
in response to the request and based on the information indicating the one or more video frames comprising the event, causing playback of the event.

13. The method of claim 12 , wherein the determining the one or more video frames is further based on correlating one or more camera angles associated with the plurality of frames with one or more expected camera angles for the event and based on audio characteristics for the event.

14. The method of claim 12 , wherein the determining the one or more video frames comprising the event further comprises:
determining a first set of frames from the one or more video frames having motion energy satisfying a threshold energy level and a second set of frames from the one or more video frames having motion energy that does not satisfy the threshold energy level.

15. The method of claim 14 , further comprising:
determining the first set of frames as comprising the event; and
determining the second set of frames as an ending of the event.

16. The method of claim 12 , wherein the determining the one or more video frames is further based on:
receiving information indicating a type of the content item;
determining a type of event from a plurality of types of events based on the type of the content item; and
determining one or more object movement patterns for the type of event.

17. The method of claim 12 , wherein the determining the one or more video frames further comprises:
using optical character recognition to analyze an on-screen scoreboard, associated with the plurality of frames, in response to determining that the event is a sporting event.

18. The method of claim 12 , further comprising:
correlating the one or more displayed clock times with a content stream time index.

19. The method of claim 1 , wherein the determining the range of video frames is further based on:
determining that the approximate time range corresponds to a first clock time and a second clock time;
performing optical character recognition on the content item to determine a first image frame that comprises the first clock time;
performing optical character recognition on the content item to determine a second image frame that comprises the second clock time;
determining that the first image frame corresponds to a beginning of the range of video frames; and
determining that the second image frame corresponds to an ending of the range of video frames.

20. The method of claim 19 , further comprising:
correlating the first clock time and the second clock time with a content stream time index.

Assignees

• Comcast Cable Comm Llc

Inventors

• Schwartz Erik
• Neumann Jan
• Sayyadi-Harikandehei Hassan
• Deichmann Stefan

Classifications

• H04N21/8456

  by decomposing the content in the time domain, e.g. in time segments · CPC title

• H04N21/84

  Generation or processing of descriptive data, e.g. content descriptors {(systems specially adapted for using meta-information in broadcast systems H04H60/73)} · CPC title

• H04N21/44008 Primary

  involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream (arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59) · CPC title

• G06T2207/30221

  Sports video; Sports image · CPC title

• G06F16/48

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title