Method and system for segmenting and transmitting on-demand live-action video in real-time

• US 9,141,860 B2
• Filed: 05/19/2011
• Issued: 09/22/2015
• Est. Priority Date: 11/17/2008
• Status: Active Grant

• Current Assignee: LiveClips, LLC
• Original Assignee: LiveClips, LLC
• Inventors: Vunic, Douglas W., Hoffert, Eric, Gessel, David
• Primary Examiner(s): Czekaj, Dave
• Assistant Examiner(s): Beck, Leron
• Application Number:
  US13/111,738
• Publication Number:
  US 20120219271A1
• Time in Patent Office: 1,587 Days
• Field of Search: 348/700
• US Class Current: 1/1
• CPC Class Codes: G06V 20/40 in video content extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44
• CPC Class Codes: G06V 20/44 Event detection
• CPC Class Codes: G06V 20/49 Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
• CPC Class Codes: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence

Abstract

A method and system for producing video-segments of a live-action event involving monitoring a live-action event for detection of event-segments, detecting one or more event-triggers with detectors, determining if an event-segment occurred based on the detected event-triggers, and editing one or more video feeds into a video-segment to encompass the event-segment.

Claims

1. A method for creating a video-segment from one or more video-feeds of a live-action event, comprising:

monitoring a live-action event for event-segments, wherein the detection of an event-segment includes the steps of

detecting one or more event-triggers with detectors within a predetermined time range, wherein at least one of the detectors comprises a speech-to-text recognition detector that detects as an event-trigger information regarding what is occurring in the live-action event,

receiving external metadata from a source other than the video-feeds and their accompanying information, and

automatically determining when an event-segment occurs by entering said event-triggers and the metadata into a predetermined profile; and

automatically editing said one or more video-feeds into a continuous video that encompasses a plurality of event-segments and that does not exceed a maximum time length, and wherein when the inclusion of all detected event segments in said video-segment would exceed said maximum time length, prioritizing inclusion of said event-segments according to their importance so that said maximum time length is not exceeded.

2. The method of claim 1, further comprising

determining if the event-state is “

on”

or “

off”

;

recording one or more of the one or more video-feeds if the event-state is determined to be “

on”

.

3. The method of claim 1, wherein at least one of the detectors comprises a frame-by-frame pattern recognition detector.

4. The method of claim 1, wherein at least one of the detectors comprise a physical sensor detectors.

5. The method of claim 1, wherein at least one of the detectors comprises an audio recognition detector.

6. The method of claim 1, wherein the live-action event is a sporting event, and the external metadata is scoring information.

7. The method of claim 1, wherein the live-action event is a sporting event, and the external metadata is scoreboard information.

8. The method of claim 1,

wherein when said event-triggers include a speech-to-text event-trigger that indicates a contrary conclusion to another event-trigger, applying a weighing factor to the speech-to-text event-trigger that is inversely proportional to the temporal differential between when the speech-to-text event trigger and the other event-triggers were registered.

9. The method of claim 8, wherein said speech-to-text recognition detector automatically detects as an event-trigger persons participating in the live-action event.

10. The method of claim 8, wherein said speech-to-text recognition detector automatically detects as an event-trigger statistical information related to what is occurring in the live-action event.

11. A method for delivering a plurality of video-segments from one or more video-feeds of a live-action event to a user device, comprising:

monitoring a live-action event for detection of event-triggers;

creating a plurality of event-segments, each event-segment created by the steps of;

detecting one or more event-triggers with detectors, wherein at least one of the detectors comprises a speech-to-text recognition detector that detects as an event-trigger information regarding what is occurring in the live-action event;

automatically determining if an important event occurred based on the detected event-triggers;

automatically editing said one or more video-feeds into an event-segment to encompass the important event;

wherein each detected event-trigger is assigned a weighted value based upon the detected event trigger;

editing a plurality of event-segments into a continuous video that does not exceed a maximum time length, wherein when the inclusion of all detected event-segments in said video would exceed said maximum time length, prioritizing inclusion of said event-segments according to their importance so that said maximum time length is not exceeded; and

presenting on said user device a selectable representation of said video.

12. The method of claim 11, wherein the weighted value assigned to each event trigger is based upon the detected event trigger exceeding a predetermined threshold.

13. The method of claim 12, wherein the weighted value assigned to each event trigger is proportional to the extent to which the detected event trigger exceeded said predetermined threshold.

14. The method of claim 11, wherein the weighted value assigned to each event trigger is based upon each detector'"'"'s predetermined relative importance to each other detector.

15. The method of claim 11, wherein the weighted value assigned to each event trigger is based upon each detector'"'"'s predetermined relative importance to each other detector that also detects an event trigger within a predetermined range of time.

16. The method of claim 11, wherein the weighted value assigned to each event trigger is based upon each detected event trigger'"'"'s predetermined relative importance to each other event trigger.

17. The method of claim 11, further comprising:

Wherein it is determined if an important event occurred based on an algorithm that is specific to the live action event.

18. The method of claim 11, wherein said algorithm is based upon the result of an operation, acted on one or more of the weighted values, being less than a predetermined value.

19. The method of claim 11, wherein said algorithm is based upon the result of an operation, acted on one or more of the weighted values, falling with a range of predetermined values.

20. The method of claim 11, wherein said algorithm is based upon the result of an operation, acted on one or more of the weighted values, being greater than a predetermined value.

21. The method of claim 11, further comprising:

recording the time that each event-trigger is detected;

determining when the important event occurred based on the recorded times of each detected event trigger.

22. The method of claim 21, wherein it is determined when the important event occurred based upon the recorded times of each event trigger that all fall within a predetermined range of time.

23. The method of claim 22, wherein one or more video feeds are edited into an event-segment to encompass the important event based on when it is determined that the important event occurred.

24. The method of claim 21, wherein one or more video feeds are edited into a video-segment to encompass the important event based on the event triggers used to determine whether the important event occurred.

25. A method for creating a mini-event from one or more video-feeds of a live-action sporting event, comprising:

monitoring the live-action event for detection of event-segments, wherein the detection of an event-segment includes the steps of;

detecting one or more event-triggers with detectors, wherein at least one of the detectors comprises a speech-to-text recognition detector that detects as an event-trigger information regarding what is occurring in the live-action event;

automatically determining if event-segment occurred based on the detected event-triggers by entering them into a predetermined profile;

automatically editing said one or more video-feeds into a video-segment to encompass said event-segment; and

automatically editing a plurality of video-segments into a continuous video mini-event that is shorter in duration than the live-action sporting event, that satisfys at least one criteria and does not exceed a maximum time length, wherein when inclusion of all detected video-segments would exceed said maximum time length, prioritizing inclusion of said video-segments according to their importance so that said maximum time length is not exceeded.

26. The method of claim 25, wherein the plurality of video-segments are edited together chronologically, and wherein only a subset of the video-segments are included in the mini-event.

27. The method of claim 25, wherein the plurality of video-segments each satisfy a pre-determined criteria explicitly designated by a user.

28. The method of claim 26, wherein the live action event is a sporting event and the criteria is events related to at least one particular player.

29. The method of claim 26, wherein the plurality of video-segments each satisfy a pre-determined criteria determined without user input based upon a user'"'"'s prior explicit behavior.

30. The method of claim 25, further comprising:

automatically editing together video-segments with video data that does not comprise a video segment.

31. The method of claim 30, further comprising,

wherein inclusion of non-video-segment video data with a series of video-segments is automatically determined based upon pre-determined mappings between certain important events and certain non-video-segment video data.

32. The method of claim 30, further comprising,

wherein inclusion of non-video-segment video data with a series of video-segments is automatically determined based upon pre-determined mappings between certain information garnered from detected event-triggers and certain non-video-segment video data.

33. The method of claim 31, further comprising:

automatically determining exclusion of certain non-video-segment video data in the series of video-segments based upon a pre-determined relative importance of assigned to the mappings.

34. The method of claim 25, further comprising:

automatically editing together video-segments with audio data that does not comprise a video segment.

35. The method of claim 34, further comprising,

wherein inclusion of non-video-segment video data with a series of video-segments is automatically determined based upon by pre-determined mappings between certain important events and certain non-video-segment audio data.

36. The method of claim 34, further comprising,

wherein inclusion of non-video-segment video data with a series of video-segments is automatically determined based upon by pre-determined mappings between certain information garnered from detected event-triggers and certain non-video-segment audio data.

37. The method of claim 35, further comprising:

automatically determining exclusion of certain non-video-segment audio data in the series of video-segments based upon a pre-determined relative importance assigned to the mappings.

38. The method of claim 25, further comprising:

editing a plurality of video-segments into another video-segment that will not exceed a predetermined time period.

39. The method of claim 38, further comprising:

automatically determining exclusion of certain video-segments into the series of video- segments based upon a pre-determined relative importance assigned to certain important events.