Identifying Content of Interest

Patent metadata

Field	Value
Publication number	US-2016110877-A1
Application number	US-201414514602-A
Country	US
Kind code	A1
Filing date	Oct 15, 2014
Priority date	Oct 15, 2014
Publication date	Apr 21, 2016
Grant date	—

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:
receiving, by a computing device, metadata identifying an event occurring in a video program; determining an expected motion of objects in the identified event; 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.

2 . The method of claim 1 , further comprising:
determining a first set of frames in the video program having motion energy satisfying a threshold energy level and a second set of frames in the video program having motion energy below the threshold energy level; and identifying the video frames in which the event occurs based on the first set of frames and the second sets of frames.

3 . The method of claim 2 , wherein identifying the video frames in which the event occurs based on the first set of frames and the second sets of frames further comprises:
identifying the first set of frames as a beginning of the video frames in which the event occurs; and identifying the second set of frames as an ending of the video frames in which the event occurs.

4 . The method of claim 1 , further comprising:
receiving first timing information associated with the event; analyzing the video program to determine second timing information; and identifying the video frames in which the event occurs by correlating the first timing information with the second timing information.

5 . The method of claim 1 , further comprising:
dividing one or more frames of the video program into a plurality of sections; determining motion energy associated with one or more of the sections; and identifying the video frames in which the event occurs based on the motion energy associated with the one or more sections.

6 . The method of claim 5 , wherein determining motion energy associated with one or more of the sections further comprises determining a first section of the one or more sections associated with movement in a first direction and a second section of the one or more sections associated with movement in a second direction.

7 . The method of claim 6 , wherein identifying the video frames in which the event occurs based on the motion energy associated with the one or more sections further comprises identifying the video frames in which the event occurs in response to determining that movement in the first direction substantially coincides with movement in the second direction.

8 . The method of claim 1 , wherein analyzing motion energy in the video program to identify video frames in which the event occurs further comprising correlating the expected motion to movement patterns identified in the video program.

9 . The method of claim 8 , wherein correlating the expected motion to movement patterns identified in the video program further comprises determining detail of the movement patterns based on processing capability.

10 . The method of claim 1 , wherein determining the expected motion of objects in the identified event further comprises:
storing a plurality of expected motion patterns for a plurality of types of events; and retrieving a first expected motion pattern from the plurality of expected motion patterns.

11 . The method of claim 1 , wherein analyzing the motion energy in the video program to identify video frames in which the event occurs further comprises analyzing motion energy according to rules of the sporting event.

12 . The method of claim 1 , further comprising:
determining one or more display views associated with the video program; and identifying the video frames based on the one or more display views.

13 . The method of claim 12 ,
wherein analyzing the motion energy in the video program to identify video frames in which the event occurs comprises analyzing motion energy in the video program associated with a first display view to identify a first set of video frames in which a first event occurs and analyzing motion energy in the video program associated with a second display view to identify a second set of video frames in which a second event occurs; and wherein storing information identifying the video frames in which the event occurs comprises storing information identifying the first set of video frames and the second set of video frames.

14 . The method of claim 12 , further comprising:
determining a change in display view in the video program from a first display view to a second display view; and identifying the video frames based on the change in display view.

15 . The method of claim 12 , wherein determining one or more display views of the video program further comprises:
determining one of a panning display view and a zoomed display view; and identifying the video frames based on a change in display view.

16 . The method of claim 1 , further comprising:
determining context of graphics displayed in the video program; and identifying the video frames in which the event occurs based on the context of the graphics.

17 . The method of claim 16 , wherein determining the context of graphics displayed in the video program further comprises determining a presence of a time indicator in the video program.

18 . The method of claim 1 , further comprising:
analyzing audio associated with the video program; and identifying the video frames in which the event occurs based on the analyzed audio.

19 . A method comprising:
receiving, by a computing device, metadata identifying one or more events occurring in a video program; determining a first display view and a second display view associated with the one or more events; analyzing motion energy in the video program based on the first and second display views to identify at least one set of video frames in which the one or more events occur; and storing information identifying the at least one set of video frames in which the one or more events occur.

20 . A method comprising:
receiving, by a computing device, metadata identifying one or more events occurring in a video program; determining at least one set of video frames in which the one or more events occur based on a correlation between an expected motion of objects associated with the one or more events and one or more movement patterns identified in the video program; and storing information identifying the at least one set of video frames in which the one or more events occur.

Assignees

• Comcast Cable Comm Llc

Inventors

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

Classifications

• G06F16/7867

  using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings · CPC title

• 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

• G06F16/745

  the internal structure of a single video sequence · CPC title

• G06T7/20 Primary

  Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51) · CPC title