Method, system, device and computer program product for MPEG variable bit rate (VBR) video traffic classification using a nearest neighbor classifier

1. A method for moving pictures experts group (MPEG) variable bit rate (VBR) video traffic classification using a nearest neighbor classifier, comprising:

determining I, P and B frame sizes for an input MPEG VBR video sequence;

computing mean values of said I, P and B frame sizes; and

classifying said input video sequence into one of a plurality of categories based on said computed mean values using a nearest neighbor classifier.

2. The method of claim 1 , wherein said classifying step comprises computing a Euclidean distance between said mean values of said I, P and B frame sizes of said input video sequence and mean values of I, P and B frame sizes of a training video sequence.

3. The method of claim 1 , wherein said classifying step comprises using a K nearest neighbor classifier.

4. The method of claim 3 , wherein said classifying step comprises using a K nearest neighbor classifier with K=3.

5. The method of claim 2 , wherein said computing step comprises determining said training sequence based on in-product and out-of-product training.

6. The method of claim 1 , wherein said classifying step comprises providing as said categories first and second categories; and

classifying said input video sequence as one of said first and second categories.

7. The method of claim 6 , wherein said providing step comprises providing as said first and second categories movies and sports categories.

8. A computer-readable medium carrying one or more sequences of one or more instructions for moving pictures experts group (MPEG) variable bit rate (VBR) video traffic classification using a nearest neighbor classifier, the one or more sequences of one or more instructions including instructions which, when executed by one or more processors, cause the one or more processors to perform the steps recited in any one of claims 1 - 7 .

9. A communications system configured to include moving pictures experts group (MPEG) variable bit rate (VBR) video traffic classification using a nearest neighbor classifier, comprising:

a device configured to determine I, P and B frame sizes for an input MPEG VBR video sequence;

said device configured to compute mean values of said I, P and B frame sizes; and

said device configured to classify said input video sequence into one of a plurality of categories based on said computed mean values using a nearest neighbor classifier.

10. The system of claim 9 , wherein said nearest neighbor classifier is configured to compute a Euclidean distance between said mean values of said I, P and B frame sizes of said input video sequence and mean values of I, P and B frame sizes of a training video sequence.

11. The system of claim 9 , wherein said nearest neighbor classifier comprises a K nearest neighbor classifier.

12. The system of claim 11 , wherein K=3.

13. The system of claim 10 , wherein said training sequence is determined based on in-product and out-of-product training.

14. The system of claim 9 , wherein said categories comprise first and second categories; and

said device is configured to classify said input video sequence as one of said first and second categories.

15. The system of claim 14 , wherein said first and second categories comprise movies and sports categories.

16. A communications system for moving pictures experts group (MPEG) variable bit rate (VBR) video traffic classification using a nearest neighbor classifier, comprising:

means for determining I, P and B frame sizes for an input MPEG VBR video sequence;

means for computing mean values of said I, P and B frame sizes; and

means for classifying said input video sequence into one of a plurality of categories based on said computed mean values using a nearest neighbor classifier.

17. A communications device configured to include moving pictures experts group (MPEG) variable bit rate (VBR) video traffic classification using a nearest neighbor classifier, comprising:

said device configured to determine I, P and B frame sizes for an input MPEG VBR video sequence;

said device configured to compute mean values of said I, P and B frame sizes; and

said device configured to classify said input video sequence into one of a plurality of categories based on said computed mean values using a nearest neighbor classifier.

18. The device of claim 17 , wherein said nearest neighbor classifier is configured to compute a Euclidean distance between said mean values of said I, P and B frame sizes of said input video sequence and mean values of I, P and B frame sizes of a training video sequence.

19. The device of claim 17 , wherein said nearest neighbor classifier comprises a K nearest neighbor classifier.

20. The device of claim 19 , wherein K=3.

21. The device of claim 18 , wherein said training sequence is determined based on in-product and out-of-product training.

22. The device of claim 17 , wherein said categories comprise first and second categories; and

said device is configured to classify said input video sequence as one of said first and second categories.

23. The device of claim 22 , wherein said first and second categories comprise movies and sports categories.

24. A communications apparatus for moving pictures experts group (MPEG) variable bit rate (VBR) video traffic classification using a nearest neighbor classifier, comprising:

means for determining I, P and B frame sizes for an input MPEG VBR video sequence;

means for computing mean values of said I, P and B frame sizes; and

means for classifying said input video sequence into one of a plurality of categories based on said computed mean values using a nearest neighbor classifier.