Video scene classification by activity

Patent metadata

Field	Value
Publication number	US-9984293-B2
Application number	US-201414513151-A
Country	US
Kind code	B2
Filing date	Oct 13, 2014
Priority date	Jul 23, 2014
Publication date	May 29, 2018
Grant date	May 29, 2018

Abstract

Video and corresponding metadata is accessed. Events of interest within the video are identified based on the corresponding metadata, and best scenes are identified based on the identified events of interest. A video summary can be generated including one or more of the identified best scenes. The video summary can be generated using a video summary template with slots corresponding to video clips selected from among sets of candidate video clips. Best scenes can also be identified by receiving an indication of an event of interest within video from a user during the capture of the video. Metadata patterns representing activities identified within video clips can be identified within other videos, which can subsequently be associated with the identified activities.

First claim

What is claimed is:

1. A method for identifying scenes in videos, the method comprising:
obtaining one or more electronic files defining a video captured with a camera, the one or more electronic files including event of interest information indicating reception of verbal input during the capture of the video, the verbal input identifying an occurrence of an event of interest within the video, the event of interest occurring at an event moment within the video, the event of interest information identifying (i) a given input type of the verbal input, input types of the verbal input including a first input type, a second input type, and a third input type, and (ii) an input moment during the capture of the video at which the verbal input was received, wherein the first input type indicates the input moment occurring before the event moment, the second input type indicates the input moment occurring during the event moment, and the third input type indicates the input moment occurring after the event moment;
identifying the input moment based on the event of interest information;
identifying the given input type of the verbal input based on the event of interest information;
identifying the event moment based on the input moment and the given input type, wherein the event moment is identified to occur before the input moment based on the given input type being the first type, the event moment is identified to occur during the input moment based on the given input type being the second type, and the event moment is identified to occur after the input moment based on the given input type being the third type;
identifying a portion of the video as a video clip associated with the event of interest based on the event of interest information, the video clip comprising a first time amount of the video occurring before the event moment and a second time amount of the video occurring after the event moment, the first time amount and the second time amount being determined based on a type of an activity captured within the video; and
storing clip information indicating the association of the video clip with the event of interest and the portion of the video included in the video clip.

2. The method of claim 1 , wherein the occurrence of the event of interest is identified further based on metadata associated with the video, the metadata captured during the capture of the video, the metadata characterizing velocity or acceleration of the activity captured within the video.

3. The method of claim 2 , wherein a metadata criteria for identifying the occurrence of the event of interest based on the metadata associated with the video is based on the type of the activity captured within the video such that a first metadata criteria is used to identify the occurrence of the event of interest based on the activity being of a first type and a second metadata criteria is used to identify the occurrence of the event of interest based on the activity being of a second type, the first metadata criteria being different from the second metadata criteria.

4. The method of claim 1 , wherein the verbal input comprises a spoken command associated with tagging events of interest.

5. The method of claim 1 , wherein the event moment includes a point in time within the video or a duration of time within the video.

6. The method of claim 1 , further comprising:
identifying one or more non-event moments within the video, the one or more non-event moments not associated with any event of interest within the video; and
storing non-event information indicating the one or more non-event moments.

7. The method of claim 6 , wherein the one or more non-event moments are identified based on matching metadata associated with the video with a metadata pattern determined to not be of interest to a user, the metadata characterizing velocity of the activity captured within the video, acceleration of the activity captured within the video, visuals captured within the video, or audio captured within the video.

8. A system for identifying scenes in videos, the system comprising:
one or more physical processors configured by computer-readable instructions to:
obtain one or more electronic files defining a video captured with a camera, the one or more electronic files including event of interest information indicating reception of verbal input during the capture of the video, the verbal input identifying an occurrence of an event of interest within the video, the event of interest occurring at an event moment within the video, the event of interest information identifying (i) a given input type of the verbal input, input types of the verbal input including a first input type, a second input type, and a third input type, and (ii) an input moment during the capture of the video at which the verbal input was received, wherein the first input type indicates the input moment occurring before the event moment, the second input type indicates the input moment occurring during the event moment, and the third input type indicates the input moment occurring after the event moment;
identify the input moment based on the event of interest information;
identify the given input type of the verbal input based on the event of interest information;
identify the event moment based on the input moment and the given input type, wherein the event moment is identified to occur before the input moment based on the given input type being the first type, the event moment is identified to occur during the input moment based on the given input type being the second type, and the event moment is identified to occur after the input moment based on the given input type being the third type;
identify a portion of the video as a video clip associated with the event of interest based on the event of interest information, the video clip comprising a first time amount of the video occurring before the event moment and a second time amount of the video occurring after the event moment, the first time amount and the second time amount being determined based on a type of an activity captured within the video; and
store clip information indicating the association of the video clip with the event of interest and the portion of the video included in the video clip.

9. The system of claim 8 , wherein the occurrence of the event of interest is identified further based on metadata associated with the video, the metadata captured during the capture of the video, the metadata characterizing velocity or acceleration of the activity captured within the video.

10. The system of claim 9 , wherein a metadata criteria for identifying the occurrence of the event of interest based on the metadata associated with the video is based on the type of the activity captured within the video such that a first metadata criteria is used to identify the occurrence of the event of interest based on the activity being of a first type and a second metadata criteria is used to identify the occurrence of the event of interest based on the activity being of a second type, the first metadata criteria being different from the second metadata criteria.

11. The system of claim 8 , wherein the verbal input comprises a spoken command associated with tagging events of interest.

12. The system of claim 8 , wherein the event moment includes a point in time within the video or a duration of time within the video.

13. The system of claim 8 , wherein the one or more physical processors are further configured by the computer-readable instructions to:
identify one or more non-event moments within the video, the one or more non-event moments not associated with any event of interest within the

Assignees

• Gopro Inc

Inventors

• Hodulik Nick
• Taylor Jonathan

Classifications

• H04N23/62

  Control of parameters via user interfaces · CPC title

• H04N23/60

  Control of cameras or camera modules · CPC title

• G11B27/22

  Means responsive to presence or absence of recorded information signals · CPC title

• G06K9/00751 Primary

  Physics · mapped topic

• G06K2009/00738

  Physics · mapped topic