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

• US 9,141,859 B2
• Filed: 11/17/2008
• 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.
• Primary Examiner(s): Czekaj, Dave
• Assistant Examiner(s): Beck, Leron
• Application Number:
  US12/272,170
• Publication Number:
  US 20100123830A1
• Time in Patent Office: 2,500 Days
• Field of Search: 348/700, 348/157, 348/153
• 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: H04N 21/4394 involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58
• CPC Class Codes: H04N 21/44008 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 Class Codes: H04N 21/8456 by decomposing the content in the time domain, e.g. in time segments
• CPC Class Codes: H04N 21/8549 Creating video summaries, e.g. movie trailer retrieval in video databases by using presentations in form of a video summary G06F16/739

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 representing a portion of a live-action sporting event from one or more video-feeds, comprising:

monitoring the live-action event video feeds;

detecting one or more event-triggers with detectors, each event trigger being registered at a specific time;

receiving external metadata from other than analysis of the video feeds and any accompanying text and audio streams;

assigning each detected event trigger a weighted value representative of the confidence that an event of interest in the live-action sporting event may have occurred and;

determining using an algorithm that is specific to the live-action event when an event-segment occurred by evaluating whether the aggregate of the weighted values of event triggers registered within a predetermined length of time that corresponds to a plurality of video frames, along with the external metadata, together indicate that an event-segment occurred;

wherein the step of evaluating includes weighting the weighted values relative to one another based on the relative reliability of the detectors to one another; and

editing one or more video feeds into the video-segment so that it is a continuous video that encompasses at least one event-segment.

2. The method of claim 1, further comprising the step of determining if the event-state is “

on”

or “

off.

3. The method of claim 2, further comprising the step of recording one or more of the one or more video-feeds if the event-state is determined to be “

on”

.

4. The method of claim 1, wherein the detectors comprise frame-by-frame pattern recognition detectors.

5. The method of claim 1, wherein the detectors comprise physical sensors.

6. The method of claim 1, wherein the detectors comprise audio recognition detectors.

7. The method of claim 1, wherein the external metadata includes scoring information regarding scoring values input into a database separately from the video feeds.

8. The method of claim 1, wherein the external metadata includes scoreboard information obtained without reference to the video feeds.

9. The method of claim 1, wherein the weighted value is assigned based upon the detected event-trigger exceeding a predetermined threshold.

10. The method of claim 1, wherein the weighted value is assigned proportionally based upon the detected event-trigger exceeding a predetermined threshold.

11. The method of claim 1, wherein each detected event-trigger is assigned a weighted value based upon the predetermined relative weight of the detector that detected the event-trigger.

12. A method as claimed in claim 11, wherein the the step of determining includes evaluating a detection by one detector in the absence of a detection by one or more other detectors.

13. A method as claimed in claim 11, wherein the weighted value is assigned to a particular event-trigger is based partially upon a detection by one detector in the presence of a detection by another detector.

14. A method as claimed in claim 1, wherein information describing the event-segment is added to the video-segment, the content of which is determined by the type of event triggers detected and the external metadata.

15. A method as claimed in claim 1, wherein one or more of the video-feeds comprise a pre-edited compilation of one or more video-feeds.

16. A method as claimed in claim 1, wherein the process of evaluating includes determining that the weighted values of one or more of the event triggers exceeds a predetermined threshold.

17. A method as claimed in claim 1, wherein the process of evaluating includes determining that the weighted values of one or more of the event triggers exceeds a predetermined range of values.

18. A method as claimed in claim 1, wherein the process of evaluating includes determining that the weighted values of one or more of the event triggers is greater than or equal to a predetermined value.

19. A method as claimed in claim 1, wherein the process of evaluating includes determining that the weighted values of one or more event triggers is less than or equal to a predetermined value.

20. A method as claimed in claim 1, wherein the process of evaluating includes determining that the weighted values of one or more event triggers equals a predetermined value.

21. A method as claimed in claim 1, wherein the algorithm is based on certain times during the live-action sporting event corresponding to predetermined event-triggers unique to the type of live-action sporting event.

22. The method of claim 1, further comprising the step of determining where an event-segment occurred based on the detected event-triggers.

23. The method of claim 22, wherein the process of evaluating includes matching the recorded time of an event-trigger corresponding to a pre-selected detector.

24. The method of claim 22, wherein the process of evaluating includes considering that an average of the recorded times of all event-triggers fall within a range of time with respect to the recorded time of an event-trigger of a pre-selected detector.

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

26. The method of claim 22, wherein one or more video feeds are edited into the video segment by beginning and ending the video-segment based on predetermined times before and after the event-segment occurred for different types of event-segments.

27. The method of claim 22, wherein only those event-triggers with equal recorded times correspond to the same event-segment.

28. A system comprising:

one or more video-feeds capturing a live-action sporting event;

event-trigger detectors;

a source of external metadata other than analysis of the video feeds and any accompanying text and audio streams;

memory storage devices;

a computer process for assigning weights to each detected event trigger;

wherein the weighted value is representative of the confidence that an event of interest in the live-action sporting event may have occurred;

a computer-processor for determining if an event-segment occurred based on the detected event-triggers;

wherein the computer-processor determines when an event-segment occurs by evaluating whether the aggregate of the weighted values of event triggers registered within a predetermined length of time, along with the external metadata, together indicate that an event-segment occurred; and

wherein the computer-processor is configured to, when it is determining whether an event-segment occurs, weight the weighted values relative to one another based on the relative reliability of the detectors to one another.

29. The system of claim 28, wherein the detectors comprise frame-by-frame pattern recognition detectors.

30. The system of claim 28, wherein the detectors comprise physical sensors.

31. The system of claim 28, wherein the detectors comprise audio recognition detectors.

32. The system of claim 28, wherein the external metadata includes scoring information from a database not derived from the video feeds.

33. The system of claim 28, wherein the external metadata includes scoreboard information detector without reference to the video feeds.

34. A method for identifying an event segment in a live-action sporting event, comprising:

monitoring at least one video feed of the live-action sporting event;

detecting one or more event-triggers with detectors;

receiving external metadata from other than analysis of the video feeds and any accompanying text and audio streams;

assigning each detected event trigger a weighted value representative of the confidence that an event of interest in the live-action sporting event may have occurred; and

determining if an event-segment occurred by evaluating whether the aggregate of the weighted values of event triggers registered within a predetermined length of time that corresponds to a plurality of video frames, along with the external metadata, together indicate that an event-segment occurred.

35. The method of claim 34, further comprising the step of determining if the event-state is “

on”

or “

off.

36. The method of claim 35, further comprising the step of recording one or more of the one or more video-feeds if the event-state is determined to be “

on”

.

37. The method of claim 34, wherein the detectors comprise frame-by-frame pattern recognition detectors.

38. The method of claim 34, wherein the detectors comprise physical sensors.

39. The method of claim 34, wherein the detectors comprise audio recognition detectors.

40. The method of claim 34, wherein the external metadata includes a scoring information detector input into a database separately from the video feeds.

41. The method of claim 34, wherein the external metadata includes scoreboard information without reference to the video feeds.

42. The method of claim 34, wherein the weighted value is assigned based upon the detected event-trigger exceeding a predetermined threshold.

43. The method of claim 34, wherein the weighted value is assigned proportionally based upon the detected event-trigger exceeding a predetermined threshold.

44. The method according to claim 34, wherein each detected event-trigger is assigned a weighted value based upon the predetermined relative weight of the detector that detected the event-trigger.

45. A method as claimed in claim 44, wherein the weighted value is assigned based upon a detection by one detector in the absence of a detection by one or more other detectors.

46. A method as claimed in claim 44, wherein the weighted value is assigned based upon a detection by one detector in the presence of a detection by another detector.

47. A method as claimed in claim 34, wherein information describing the event-segment is added to the video-segment, the content of which is determined by the types of event triggers detected and the external metadata.

48. A method as claimed in claim 34, wherein one or more of the video-feeds comprise a pre-edited compilation of one or more video-feeds.

49. The method of claim 34, wherein it is determined if an event-segment occurred based on an algorithm that is specific to the live-action event.

50. A method as claimed in claim 49, wherein the process of evaluating includes determining that on one or more of weighted values exceeds a predetermined threshold.

51. A method as claimed in claim 49, wherein the process of evaluating includes determining that on one or more weighted values exceeds a predetermined range of values.

52. A method as claimed in claim 49, wherein the process of evaluating includes determining that one or more of weighted values is greater than or equal to a predetermined value.

53. A method as claimed in claim 49, wherein the process of evaluating includes determining that one or more of weighted values is less than or equal to a predetermined value.

54. A method as claimed in claim 49, wherein the process of evaluating includes determining that one or more of the weighted values equals a predetermined value.

55. A method as claimed in claim 49, wherein the process of evaluating includes accounting for the fact that certain times during the live-action sporting event correspond to predetermined event-triggers unique to the type of live-action sporting event.

56. The method of claim 34, further comprising the step of determining where an event-segment occurred based on the detected event-triggers.

57. The method of claim 56, wherein the process of evaluating includes matching the recorded time of an event-trigger corresponding to a pre-selected detector.

58. The method of claim 34, wherein the process of evaluating includes considering that all event-triggers falling within a range of time within the time recorded for the event-trigger of said pre-selected detector correspond to the same event-segment.

59. The method of claim 56, wherein the process of evaluating includes considering that event-segment is more likely to have occurred when an average of the recorded times of all event-triggers fall within a range of time with respect to the recorded time of an event-trigger of a pre-selected detector.

60. The method of claim 56, wherein only those event-triggers with equal recorded times correspond to the same event-segment.