System and method of generating video from video clips based on moments of interest within the video clips

• US 9,721,611 B2
• Filed: 10/20/2015
• Issued: 08/01/2017
• Est. Priority Date: 10/20/2015
• Status: Active Grant

• Current Assignee: GoPro, Inc.
• Original Assignee: GoPro, Inc.
• Inventors: Matias, Joven, Phan, Ha
• Primary Examiner(s): Chowdhury, Nigar
• Application Number:
  US14/918,321
• Publication Number:
  US 20170110151A1
• Time in Patent Office: 651 Days
• Field of Search: 386278-287
• CPC Class Codes: G06V 20/41 Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items segmenting video sequences G06V20/49
• CPC Class Codes: G06V 20/47 Detecting features for summarising video content
• CPC Class Codes: G06V 20/48 Matching video sequences
• CPC Class Codes: G11B 27/031 Electronic editing of digitised analogue information signals, e.g. audio or video signals
• CPC Class Codes: G11B 27/3081 used signal is a video-frame or a video-field (P.I.P)
• CPC Class Codes: G11B 27/34 Indicating arrangements indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D

Abstract

Videos may be automatically generated using a set of video clip. Individual moments of interest may be identified within individual video clips of a set of video clips. A moment of interest may correspond to a point in time within a video clip. The point in time may be associated with one or more values of one or more attributes of the video clip. Individual moments of interest may be associated with individual portions of a video. The video may be generated using the set of video clips based on the associations.

Claims

1. A system configured for generating videos from video clips based on one or more moments of interest within individual ones of the video clips, the system comprising:

one or more physical processors configured by machine-readable instructions to;

identify one or more moments of interest within individual video clips of a set of video clips for generating a video, individual moments of interest being associated with values of attributes of the video clips, the set of video clips comprising a first video clip and a second video, such that;

a first moment of interest is identified within the first video clip, the first moment of interest corresponding to a first point in time within the first video clip, the first point in time being associated the first video clip having a first value of a first attribute; and

a second moment of interest is identified within the second video clip, the second moment of interest corresponding to a second point in time within the second video clip, the second point in time being associated with the second video clip having a second value of a second attribute;

associate individual moments of interest with individual portions of a video, the associations including a first association of the first moment of interest with a first portion of the video, and a second association of the second moment of interest with a second portion of the video;

generate the video using the set of video clips based on the associations, such that the video is generated using the first video clip based on the first association and the second video clip based on the second association; and

wherein first moment of interest is identified within the first video clip by;

determining individual values of individual attributes of the first video clip, including determining that a value of the first attribute of the first video clip is the first value;

determining a first preference of the user, the first preference specifying one or more values of the first attribute of the video clips;

determining whether the value of the first attribute of the first video clip matches at least one of the one or more values of the first attribute specified by the first preference;

responsive to the first preference specifying at least the first value of the first attribute, determining that the first point in time within the first video clip is associated with the first video clip having the first value of the first attribute; and

associating the first point in time with the first moment of interest, the association facilitating identification of the first moment of interest within the first video clip.

2. The system of claim 1, wherein identifying the first moment of interest within the first video clip is based on a user-initiated identification of the first moment of interest.

3. The system of claim 2, wherein the user-initiated identification of the first moment of interest is provided either during capture of the first video clip or post capture of the first video clip.

4. The system of claim 1, wherein determining the first preference of the user is based on one or more of:

monitoring system usage by the user;

monitoring usage of one or more applications external to the system by the user;

or

obtaining entry and/or selection of the first preference from the user.

5. The system of claim 1, wherein generating the video using the set of video clips based on the associations comprises:

identifying a first segment of the first video clip, the first segment being associated with the first moment of interest, the first segment comprising a first temporal span of the first video clip, the first temporal span being associated with first attribute of the first video clip having the first value;

identifying a second segment of the second video clip, the second segment being associated with the second moment of interest, the second segment comprising a second temporal span of the second video clip, the second temporal span being associated with the second attribute of the second video clip having the second value;

providing the first segment as the first portion of the first video; and

providing the second segment as the second portion of the first video.

6. The system of claim 5, wherein providing the first segment as the first portion of the video comprises changing a temporal length of one or both of the first segment or the first portion such that that the first segment and the first portion have the same temporal length.

7. The system of claim 6, wherein generating the video further comprises:

providing supplemental audio to replace or add to audio of one or both of the first video clip or second video clip.

8. The system of claim 7, wherein providing the supplemental audio comprises synchronizing a transition between an end of the first portion of the video and a start of the second portion of the video with the supplemental audio.

9. The system of claim 8, wherein the supplemental audio comprises a song, and wherein synchronizing the transition between the end of the first portion and the start of the second portion of the video with the supplemental audio comprises synchronizing the transition with a beat of the song.

10. A method of generating videos from video clips based on one or more moments of interest within individual ones of the video clips, the method being implemented in a computer system comprising one or more physical processor and storage media storing machine-readable instructions, the method comprising:

identifying one or more moments of interest within individual video clips of a set of video clips for generating a video, individual moments of interest being associated with values of attributes of the video clips, the set of video clips comprising a first video clip and a second video, including identifying;

a first moment of interest within the first video clip, the first moment of interest corresponding to a first point in time within the first video clip, the first point in time being associated the first video clip having a first value of a first attribute; and

a second moment of interest within the second video clip, the second moment of interest corresponding to a second point in time within the second video clip, the second point in time being associated with the second video clip having a second value of a second attribute;

associating individual moments of interest with individual portions of the video, the associations including a first association of the first moment of interest with a first portion of the video, and a second association of the second moment of interest with a second portion of the video;

generating the video using the set of video clips based on the associations, such that the video is generated using the first video clip based on the first association and the second video clip based on the second association; and

wherein identifying the first moment of interest within the first video clip comprises;

determining individual values of individual attributes of the first video clip, including determining that a value of the first attribute of the first video clip is the first value;

determining a first preference of the user, the first preference specifying one or more values of the first attribute of the video clips;

determining whether the value of the first attribute of the first video clip matches at least one of the one or more values of the first attribute specified by the first preference;

responsive to the first preference specifying at least the first value of the first attribute, determining that the first point in time within the first video clip is associated with the first video clip having the first value of the first attribute; and

associating the first point in time with the first moment of interest, the association facilitating identification of the first moment of interest within the first video clip.

11. The method of claim 10, wherein identifying the first moment of interest within the first video clip is based on a user-initiated identification of the first moment of interest.

12. The method of claim 11, wherein the user-initiated identification of the first moment of interest is provided either during capture of the first video clip or post capture of the first video clip.

13. The method of claim 10, wherein determining the first preference of the user is based on one or more of:

monitoring system usage by the user;

monitoring usage of one or more applications external to the system by the user;

or

obtaining entry and/or selection of the first preference from the user.

14. The method of claim 10, wherein generating the video using the set of video clips based on the associations comprises:

identifying a first segment of the first video clip, the first segment being associated with the first moment of interest, the first segment comprising a first temporal span of the first video clip, the first temporal span being associated with first attribute of the first video clip having the first value;

identifying a second segment of the second video clip, the second segment being associated with the second moment of interest, the second segment comprising a second temporal span of the second video clip, the second temporal span being associated with the second attribute of the second video clip having the second value;

providing the first segment as the first portion of the first video; and

providing the second segment as the second portion of the first video.

15. The method of claim 14, wherein providing the first segment as the first portion of the video comprises changing a temporal length of one or both of the first segment or the first portion such that that the first segment and the first portion have the same temporal length.

16. The method of claim 15, wherein generating the video further comprises:

providing supplemental audio to replace or add to audio of one or both of the first video clip or second video clip.

17. The method of claim 16, wherein providing the supplemental audio comprises synchronizing a transition between an end of the first portion of the video and a start of the second portion of the video with the supplemental audio.

18. The method of claim 17, wherein the supplemental audio comprises a song, and wherein synchronizing the transition between the end of the first portion and the start of the second portion of the video with the supplemental audio comprises synchronizing the transition with a beat of the song.