IP Library › Granted Patent US 7,047,157
Granted Patent B2
US 7,047,157 · App. 10/976,714 · Granted May 16, 2006

Processing of video content

Assignee: Sharp Laboratories of America, Inc.
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 7,047,157
App. No.
10/976,714
Granted
May 16, 2006
Kind
B2
Abstract

Processing of video content including sports.

Claims (59)

1. A method of processing a video including sports comprising:

(a) providing a plurality of segments of said video that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame; and

(b) identifying each of said segments based upon a probabilistic inference technique, where each of said segments includes a plurality of frames of said video, wherein said probabilistic inference technique includes a Hidden Markov Model.

2. A method of processing a video including sports comprising:

(a) providing a plurality of segments of said video that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame; and

(b) identifying each of said segments based upon a probabilistic inference technique, where each of said segments includes a plurality of frames of said video, wherein said probabilistic inference technique is applied to pre-identified segments.

3. A method of processing a video including sports comprising:

(a) providing a plurality of segments of said video that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame; and

(b) identifying each of said segments based upon a probabilistic inference technique, where each of said segments includes a plurality of frames of said video, wherein said probabilistic inference technique is free from being applied to pre-identified segments.

4. A method of processing a video including sports comprising:

(a) providing a plurality of segments of said video that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame; and

(b) identifying each of said segments based upon a probabilistic inference technique, where each of said segments includes a plurality of frames of said video, wherein said probabilistic inference technique uses training sequences of segments.

5. A method of processing a video including sports comprising:

(a) providing a plurality of segments of said video that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame; and

(b) identifying each of said segments based upon a probabilistic inference technique, where each of said segments includes a plurality of frames of said video;

(c) providing another plurality of segments of said video temporally following the said plurality of segments that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame;

(d) identifying each of said another segments based upon said deterministic inference technique, where each of said another segments includes a plurality of frames of said video.

6. The method of claim 5 further comprising annotating a plurality of said segments of said video.

7. A method of processing a video including sports comprising:

(a) providing a plurality of segments of said video that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame; and

(b) identifying each of said segments based upon a deterministic inference technique, where each of said segments includes a plurality of frames of said video.

8. A method of processing a video including sports comprising:

(a) providing a plurality of segments of said video that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame; and

(b) identifying each of said segments based upon a deterministic inference technique, where each of said segments includes a plurality of frames of said video, wherein said deterministic inference technique is applied to pre-identified segments.

9. A method of processing a video including sports comprising:

(a) providing a plurality of segments of said video that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame; and

(b) identifying each of said segments based upon a deterministic inference technique, where each of said segments includes a plurality of frames of said video, wherein said deterministic inference technique is free from being applied to pre-identified segments.

10. A method of processing a video including sports comprising:

(a) providing a plurality of segments of said video that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame; and

(b) identifying each of said segments based upon a deterministic inference technique, where each of said segments includes a plurality of frames of said video, wherein said deterministic inference technique includes a measure of the green portions of a frame.

11. A method of processing a video including sports comprising:

(a) providing a plurality of segments of said video that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame; and

(b) identifying each of said segments based upon a deterministic inference technique, where each of said segments includes a plurality of frames of said video, wherein said deterministic inference technique includes a measure of motion within a plurality of frames.

12. The method of claim 11 wherein said measure of motion includes a color histogram difference.

13. A method of processing a video including sports comprising:

(a) providing a plurality of segments of said video that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame; and

(b) identifying each of said segments based upon a deterministic inference technique, where each of said segments includes a plurality of frames of said video, wherein said deterministic inference technique includes a measure of the length of a segment.

14. The method of claim 13 wherein said measure of the length identifies a segment including said scoreboard frame.

15. A computer implemented method of processing a video including sports comprising:

(a) a computer providing a plurality of segments of said video that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame; and

(b) a computer identifying each of said segments based upon a probabilistic inference technique free from manual selection by a user, where each of said segments includes a plurality of frames of said video.

16. The method of claim 15 wherein said probabilistic inference technique includes a Hidden Markov Model.

17. The method of claim 15 wherein said probabilistic inference technique is applied to pre-identified segments.

18. The method of claim 15 wherein said probabilistic inference technique is free from being applied to pre-identified segments.

19. The method of claim 15 wherein said probabilistic inference technique uses training sequences of segments.

20. The method of claim 15 further comprising

(a) a computer providing another plurality of segments of said video temporally following the said plurality of segments that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame; and

(b) a computer identifying each of said another segments based upon said deterministic inference technique, where each of said another segments includes a plurality of frames of said video.

21. The method of claim 20 further comprising a computer annotating a plurality of said segments of said video.

22. A computer implemented method of processing a video including sports comprising:

(a) a computer providing a plurality of segments of said video that includes a scoreboard frame, temporally followed by a side-line frame, and temporally followed by an end-zone frame; and

(b) a computer identifying each of said segments based upon a deterministic inference technique free from manual selection by a user, where each of said segments includes a plurality of frames of said video.

23. The method of claim 22 wherein said deterministic inference technique is applied to pre-identified segments.

24. The method of claim 22 wherein said deterministic inference technique is free from being applied to pre-identified segments.

25. The method of claim 22 wherein said deterministic inference technique includes a measure of the green portions of a frame.

26. The method of claim 22 wherein said deterministic inference technique includes a measure of motion within a plurality of frames.

27. The method of claim 26 wherein said measure of motion includes a color histogram difference.

28. The method of claim 22 wherein said deterministic inference technique includes a measure of the length of a segment.

29. The method of claim 28 wherein said measure of the length identifies a segment including said scoreboard frame.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 15, 2010
From: SHARP LABORATORIES OF AMERICA INC.
To: SHARP KABUSHIKI KAISHA
Reel/Frame 024066/0949 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 30, 2004
From: BAOXIN, LI
To: SHARP LABORATORIES OF AMERICA, INC.
Reel/Frame 015948/0665 →
Continuity (2)
Continuation 1040498700 · Mar 31, 2003
Related Publication 20050114907A1 · May 26, 2005