System and method for automatic encoder adjustment based on transport data

1. A system for transmission of a video stream as individual data streams to be communicated across a plurality of connected networks, each of the networks having a corresponding available bandwidth, the system comprising:

a processor operating in conjunction with computer memory configured to:

encode frames of the video stream for generating the individual video streams according to at least one encoding parameter for said each network of the plurality of connected networks for transmission at an estimated maximum bit rate derived based on a predicted available bandwidth available across all of the plurality of connected networks;

compare the encoded frames of the plurality of encoded frames with input frames to determine a fitness metric reflective of visual quality of the encoded frames upon detecting a change in the predicted available bandwidth determined from feedback data corresponding to said each network; and

receive data corresponding to the corresponding available bandwidth for said each network of the plurality of connected networks over which the video stream is transmitted; and

adjust the at least one encoding parameter for each of the individual video streams based on the corresponding available bandwidth of said each network and on the fitness metric by iteratively adjusting the at least one encoding parameter until the fitness metric meets or exceeds a pre-defined minimum value to optimize visual quality of the video stream for a bit rate determined based at least on the corresponding available bandwidth of said each network of the plurality of networks.

2. The system of claim 1 , wherein the input frames are provided from a video capture device.

3. The system of claim 1 , further comprising a pre-processor that processes frames prior to encoding, and wherein the input frames are provided to the processor from the pre-processor.

4. The system of claim 3 , wherein the input frames are scaled versions of frames captured by a video capture device.

5. The system of claim 1 , wherein the processor is configured to transmit encoded frames over a network of the plurality of networks.

6. The system of claim 1 , wherein the processor applies at least one of Structural Simularity (SSIM), Peak Signal to Noise Ratio (PSNR), Mean Squared Error (MSE), and Multi-Scale SSIM (MS-SSIM) to determine the fitness metric.

7. The system of claim 1 , wherein the at least one encoding parameter comprises one or more of a frame rate, an encoding rate and a frame size.

8. The system of claim 1 , wherein the processor is adapted to adjust the at least one encoding parameter based on a complexity level of the video stream.

9. The system of claim 8 , wherein the complexity level of the video stream is determined based on motion estimation analysis of the input frames of the video stream.

10. A method for transmitting a video stream as individual data streams to be communicated across a plurality of connected networks, each of the networks having a corresponding available bandwidth, the method comprising:

encoding frames of the video stream for generating the individual video streams according to at least one encoding parameter for said each network of the plurality of connected networks for transmission at an estimated maximum bit rate derived based on a predicted available bandwidth available across all of the plurality of connected networks;

comparing the encoded frame with an input frame to determine a fitness metric reflective of visual quality of the encoded frame upon detecting a change in the predicted available bandwidth determined from feedback data corresponding to said each network;

receive data corresponding to the corresponding available bandwidth for said each network of the plurality of connected networks over which the video stream is transmitted; and

adjusting the at least one encoding parameter for each of the individual video streams based on the corresponding available bandwidth of said each network and on the fitness metric by iteratively adjusting the at least one encoding parameter until the fitness metric meets or exceeds a pre-defined minimum value to optimize visual Quality of the video stream for a bit rate determined based at least on the corresponding available bandwidth of said network of the plurality of networks.

11. The method of claim 10 , further comprising:

encoding a further frame of the video stream according to the adjusted at least one encoding parameter.

12. The method of claim 10 , further comprising capturing the input frame.

13. The method of claim 10 , further comprising:

pre-processing the input frame, the pre-processing comprising scaling the input frame.

14. The method of claim 10 , wherein the fitness metric is determined based on at least one of Structural Similarity (SSIM), Peak Signal to Noise Ratio (PSNR), Mean Squared Error (MSE), and Multi-Scale SSIM (MS-SSIM).

15. The method of claim 10 , wherein the at least one encoding parameter comprises one or more of a frame rate, an encoding rate and a frame size.

16. The method of claim 10 , further comprising adjusting the at least one encoding parameter based on a correlated parameter.

17. The method of claim 16 , wherein the correlated parameter is a packet loss rate.

18. The method of claim 10 , further comprising adjusting the at least one encoding parameter based on a maximum bit rate.

19. The method of claim 10 , further comprising adjusting the at least one encoding parameter based on a complexity level of the video stream.

20. The method of claim 19 , wherein the complexity level of the video stream is determined based on motion estimation analysis of the input frames of the video stream.