IP Library › Granted Patent US 8,451,907
Granted Patent B2
US 8,451,907 · App. 12/202,839 · Granted May 28, 2013

Methods and apparatus to detect transport faults in media presentation systems

Inventor: Amy Ruth Reibman (Chatham, NJ)
Assignee: AT&T Intellectual Property I, L.P.
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 8,451,907
App. No.
12/202,839
Granted
May 28, 2013
Kind
B2
Abstract

Example methods and apparatus to detect transport faults in media presentation systems are disclosed. An example method comprises decoding a media stream to form audio data and pixel data, computing a first value representative of the media stream using pixel data associated with a first set of the video frames, computing a second value representative of the media stream using pixel data associated with a second set of the video frames, computing a third value representative of first speech in a first segment of the audio data, computing a fourth value representative of second speech in a second segment of the audio data, determining a fifth value representative of a likelihood that a transport failure has affected the media stream, the fifth value determined using the first, second, third and fourth values, and comparing the fifth value to a threshold to determine whether to generate a transport failure alert.

Claims (74)

1. A method comprising:

decoding a media stream to form audio data and pixel data for each of a plurality of video frames;

computing a first value representative of the media stream over a first set of the video frames using pixel data associated with the first set of the video frames;

computing a second value representative of the media stream over a second set of the video frames using pixel data associated with the second set of the video frames;

computing a third value representative of first speech in a first segment of the audio data;

computing a fourth value representative of second speech in a second segment of the audio data;

determining a fifth value representative of a likelihood that a transport failure has affected the media stream, the fifth value determined by:

computing a first difference between the first and second values;

computing a second difference between the third and fourth values; and

computing the fifth value as a weighted sum of the first and second differences; and

comparing the fifth value to a threshold to determine whether to generate a transport failure alert.

2. A method as defined in claim 1 , further comprising:

computing a sixth value representative of a first luminance in the first set of the video frames; and

computing a seventh value representative of a second luminance in the second set of the video frames, wherein the fifth value is further determined using the sixth and seventh values, the first value is representative of a first interframe change range, the second value is representative of a second interframe change rate, and the second difference is representative of at least one of interrupted speech or silence.

3. A method as defined in claim 2 , wherein the fifth value is further determined by:

computing a third difference between the sixth and seventh values; and

computing the fifth value as a weighted sum of the first, second and third differences.

4. A method as defined in claim 2 , wherein the fifth value is further determined by:

comparing the first difference to a second threshold to determine an eighth value;

comparing the second difference to a third threshold to determine a ninth value;

computing a third difference between the sixth and seventh values;

comparing the third difference to a fourth threshold to determine a tenth value; and

computing the fifth value as a weighted sum of the eighth, ninth and tenth values.

5. A method as defined in claim 2 , wherein the fifth value is further determined by:

computing a third difference between the sixth and seventh values; and

setting the fifth value to a value exceeding the threshold when a majority of the first, second and third differences are representative of a possible transport failure.

6. A method as defined in claim 1 , wherein the fifth value exceeds the threshold and the transport failure alert is sent when the first value is representative of high-motion video, the second value is representative of still-motion video, the third value is representative of speech and the fourth value is representative of at least one of interrupted speech or silence.

7. A method as defined in claim 1 , wherein computing the fourth value comprises:

detecting a first phoneme of a spoken word in the audio data; and

determining whether a subsequent phoneme of the spoken word is absent in the audio data.

8. A method as defined in claim 1 , further comprising determining whether a scene change occurred; and wherein determining the fifth value comprises not using the first and second values when the scene change occurred.

9. An apparatus comprising:

a video decoder to decode a media stream to form pixel data for each of a plurality of video frames;

an audio decoder to decode the media stream to form audio data;

a motion continuity detector to compute a first value representative of the media stream over a first set of the video frames using pixel data associated with the first set of the video frames, and a second value representative of the media stream over a second set of the video frames using pixel data associated with the second set of the video frames;

a speech continuity detector to compute a third value representative of first speech in a first segment of the audio data, and a fourth value representative of second speech in a second segment of the audio data; and

a failure decision controller to determine a fifth value representative of a likelihood that a transport failure has affected the media stream and to compare the fifth value to a threshold to determine whether to generate a transport failure alert, the fifth value determined by:

computing a first difference between the first and second values;

computing a second difference between the third and fourth values; and

computing the fifth value as a weighted sum of the first and second differences.

10. An apparatus as defined in claim 9 , further comprising:

a luminance continuity detector to compute a sixth value representative of a first luminance in the first set of the video frames, and a seventh value representative of a second luminance in the second set of the video frames, wherein the failure decision controller is to further determine the fifth value using the sixth and seventh values, the first value is representative of a first interframe change range, the second value is representative of a second interframe change rate, and the second difference is representative of at least one of interrupted speech or silence.

11. An apparatus as defined in claim 10 , wherein the failure decision controller is to further determine the fifth value by:

computing a third difference between the sixth and seventh values; and

computing the fifth value as a weighted sum of the first, second and third differences.

12. An apparatus as defined in claim 10 , wherein the failure decision controller is to further determine the fifth value by:

computing a third difference between the sixth and seventh values; and

setting the fifth value to a value exceeding the threshold when a majority of the first, second and third differences are representative of a possible transport failure.

13. An apparatus as defined in claim 9 , wherein the fifth value exceeds the threshold and the transport failure alert is sent when the first value is representative of high-motion video, the second value is representative of still-motion video, the third value is representative of speech and the fourth value is representative of at least one of interrupted speech or silence.

14. An apparatus as defined in claim 9 , wherein the speech continuity detector is to compute the fourth value by:

detecting a first phoneme of a spoken word in the audio data; and

determining whether a subsequent phoneme of the spoken word is absent in the audio data.

15. An apparatus as defined in claim 9 , further comprising a scene continuity detector to determine whether a scene change occurred, wherein the failure decision controller is to determine the fifth value without using the first and second values when the scene change occurred.

16. A storage device comprising machine readable instructions which, when executed, cause a machine to perform operations comprising:

decoding a media stream to form audio data and pixel data for each of a plurality of video frames;

computing a first value representative of the media stream over a first set of the video frames using pixel data associated with the first set of the video frames;

computing a second value representative of the media stream over a second set of the video frames using pixel data associated with the second set of the video frames;

computing a third value representative of first speech in a first segment of the audio data;

computing a fourth value representative of second speech in a second segment of the audio data;

determining a fifth value representative of a likelihood that a transport failure has affected the media stream, the fifth value determined by:

computing a first difference between the first and second values;

computing a second difference between the third and fourth values; and

computing the fifth value as a weighted sum of the first and second differences; and

comparing the fifth value to a threshold to determine whether to generate a transport failure alert.

17. A storage device as defined in claim 16 , wherein the operations further comprise:

computing a sixth value representative of a first luminance in the first set of the video frames; and

computing a seventh value representative of a second luminance in the second set of the video frames, wherein determining the fifth value is further comprises using the sixth and seventh values, the first value is representative of a first interframe change range, the second value is representative of a second interframe change rate, and the second difference is representative of at least one of interrupted speech or silence.

18. A storage device as defined in claim 17 , wherein determining the fifth value comprises:

computing a third difference between the sixth and seventh values; and

setting the fifth value to a value exceeding the threshold when a majority of the first, second and third differences are representative of a possible transport failure.

19. A storage device as defined in claim 16 , wherein the fifth value exceeds the threshold and the transport failure alert is sent when the first value is representative of high-motion video, the second value is representative of still-motion video, the third value is representative speech and the fourth value is representative at least one of interrupted speech or silence.

20. A storage device as defined in claim 16 , wherein computing the fourth value comprises:

detecting a first phoneme of a spoken word in the audio data; and

determining whether a subsequent phoneme of the spoken word is absent in the audio data.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 9, 2008
From: REIBMAN, AMY RUTH
To: AT&T INTELLECTUAL PROPERTY I, L.P.
Reel/Frame 021515/0424 →
Continuity (1)
Related Publication 20100054340A1 · Mar 4, 2010