Full reference video quality measurements of video conferencing over the congested networks

1. A computer implemented method of processing a received video stream, comprising:

identifying a number of repeated video frames within a sequence of N video frames within the video stream, where N is an integer greater than 1;

determining, using a video frame quality assessment mechanism adapted to use repeated frames information, a motion adapted (MA) video quality metric (VQM) of the sequence of N video frames; and

generating an alarm in response to the motion adapted VQM being less than a threshold level;

wherein said motion adapted VQM of the sequence of N video frames is calculated as:

V

⁢

Q

⁢

M

M

⁢

A

(

f

ˆ

,

g

)

=

∑

i

=

1

M

V

⁢

Q

⁢

M

i

2

(

f

ι

^

,

g

i

)

N

,

wherein N is a number of video frames within a video frame sequence f, and M is a number of video frames within a received video frame sequence g.

2. The method of claim 1 , wherein the method is repeated for each of a plurality of video stream segments within the video stream.

3. The method of claim 2 , wherein each of the video stream segments comprises a respective sequence of N video frames.

4. The method of claim 1 , further comprising transmitting the alarm toward a network manager, the alarm configured to cause the network manager to reduce congestion on at least one link associated with the received video stream.

5. The method of claim 1 , further comprising transmitting the alarm toward a server, the alarm configured to cause the server to adjust encoding or transcoding associated with the received video stream.

6. The method of claim 1 , wherein the video frame quality assessment mechanism comprises a Visual Information Fidelity (VIF) assessment mechanism.

7. The method of claim 1 , wherein the video frame quality assessment mechanism comprises a Video Multimethod Assessment Fusion (VMAF) assessment mechanism.

8. The method of claim 1 , wherein the video frame quality assessment mechanism comprises one of a Structural Similarity (SSIM) and a Multi-Scale Structural Similarity (MS-SSIM) assessment mechanism.

9. The method of claim 1 , wherein the video frame quality assessment mechanism comprises a peak signal-to-noise ratio (PSNR) assessment mechanism.

10. The method of claim 1 , wherein N is selected as a number of frames within a group of frames (GOF) or group of pictures (GOP) structure used to encode the video stream.

11. The method of claim 1 , wherein N is selected as a number of frames associated with a predetermined presentation time associated with the video stream.

12. The method of claim 11 , wherein N is selected as a number of frames associated with one second of presentation time of the video stream.

13. The method of claim 11 , wherein N is selected as a number of frames associated with an integer multiple of one half second of presentation time of the video stream.

14. A system, comprising:

one or more computer processors; and

memory storing program instructions that are executed by the one or more processors to implement a video quality analyzer configured for:

identifying a number of repeated video frames within a sequence of N video frames within the video stream, where N is an integer greater than 1;

determining, using a video frame quality assessment mechanism adapted to use repeated frames information, a motion adapted (MA) video quality metric (VQM) of the sequence of N video frames; and

generating an alarm in response to the motion adapted VQM being less than a threshold level;

wherein said motion adapted VQM of the sequence of N video frames is calculated as:

V

⁢

Q

⁢

M

M

⁢

A

(

f

ˆ

,

g

)

=

∑

i

=

1

M

V

⁢

Q

⁢

M

i

2

(

f

ι

^

,

g

i

)

N

,

wherein N is a number of video frames within a video frame sequence f, and M is a number of video frames within a received video frame sequence g.

15. The system of claim 14 , wherein the video quality analyzer is further configured for processing each of a plurality of video stream segments within the video stream.

16. The system of claim 14 , wherein the video quality analyzer is further configured for transmitting the alarm toward a network manager, the alarm configured to cause the network manager to reduce congestion on at least one link associated with the received video stream.

17. The system of claim 14 , wherein the video quality analyzer is further configured for transmitting the alarm toward a server, the alarm configured to cause the server to adjust encoding or transcoding associated with the received video stream.

18. The system of claim 14 , wherein the video frame quality assessment mechanism comprises one of a Visual Information Fidelity (VIF) assessment mechanism and a Video Multimethod Assessment Fusion (VMAF) assessment mechanism.

19. The system of claim 14 , wherein the video frame quality assessment mechanism comprises one of a Structural Similarity (SSIM) and a Multi-Scale Structural Similarity (MS-SSIM) assessment mechanism.

20. A computer implemented video quality analyzer for qualitatively assessing received video streams comprising non-transitory compute and memory resources configured for:

identifying a number of repeated video frames within a sequence of N video frames within a video stream, where N is an integer greater than 1;

determining, using a video frame quality assessment mechanism adapted to use repeated frames information, a motion adapted (MA) video quality metric (VQM) of the sequence of N video frames; and

generating an alarm in response to the motion adapted VQM being less than a threshold level;

wherein said motion adapted VQM of the sequence of N video frames is calculated as:

V

⁢

Q

⁢

M

M

⁢

A

(

f

ˆ

,

g

)

=

∑

i

=

1

M

V

⁢

Q

⁢

M

i

2

(

f

ι

^

,

g

i

)

N

,

wherein N is a number of video frames within a video frame sequence f, and M is a number of video frames within a received video frame sequence g.