US2022014758A1PendingUtilityA1

System and method for controlling video coding within image frame

Assignee: SZ DJI TECHNOLOGY CO LTDPriority: Nov 30, 2017Filed: Sep 27, 2021Published: Jan 13, 2022
Est. expiryNov 30, 2037(~11.4 yrs left)· nominal 20-yr term from priority
H04N 19/197H04N 19/142H04N 19/115H04N 19/124H04N 19/149H04N 19/172H04N 19/174
56
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

A method for controlling video coding includes: obtaining an image frame from a video stream, wherein the image frame is associated with a coding control model; encoding the image frame using a quantization parameter (QP) calculated based on the coding control mode; determining whether a scene has changed significantly based on an analysis of the encoded image frame; in response to the scene having changed significantly, initializing parameters for the coding control model; and in response to no significant scene change, updating the parameters for the coding control model.

Claims

exact text as granted — not AI-modified
What is claimed is: 
     
         1 . A method for controlling video coding comprising:
 obtaining an image frame from a video stream, wherein the image frame is associated with a coding control model;   encoding the image frame using a quantization parameter (QP) calculated based on the coding control model;   determining whether a scene has changed significantly based on an analysis of the encoded image frame;   in response to the scene having changed significantly, initializing parameters for the coding control model; and   in response to no significant scene change, updating the parameters for the coding control model.   
     
     
         2 . The method of  claim 1 , further comprising, after obtaining the image frame from the video stream:
 determining whether the image frame is a first image frame of the video stream; and   in response to the image frame being the first image frame, initializing the parameters for the coding control model.   
     
     
         3 . The method of  claim 1 , further comprising, after obtaining the image frame from the video stream:
 obtaining a target bit rate for the image frame; and   calculating a bits-per-pixel (bpp) rate based on the target bit rate for the image frame.   
     
     
         4 . The method of  claim 1 , wherein:
 the coding control model includes a logarithm rate-quantization model or a quadratic rate-quantization model.   
     
     
         5 . The method of  claim 4 , wherein:
 in the logarithm rate-quantization model, a logarithm function of a target bit rate for the image frame is a linear function of the QP; and   initializing the parameters for the rate control model includes initializing parameters of the linear function.   
     
     
         6 . The method of  claim 5 , wherein:
 updating the parameters for the rate control model includes updating the parameters of the linear function.   
     
     
         7 . The method of  claim 5 , wherein:
 updating the parameters for the rate control model includes updating the parameters of the linear function through a learning rate based on a random gradient decent algorithm.   
     
     
         8 . The method of  claim 7 , wherein:
 the learning rate is pre-configured.   
     
     
         9 . The method of  claim 7 , wherein:
 the learning rate is determined dynamically.   
     
     
         10 . A video encoder comprising:
 a memory storing one or more computer-executable instructions; and   one or more processors configured to access the memory and execute the one or more computer-executable instructions to:
 obtain an image frame from a video stream, wherein the image frame is associated with a coding control model; 
 encode the image frame using a quantization parameter (QP) calculated based on the coding control model; 
 determine whether a scene has changed significantly based on an analysis of the encoded image frame; 
 in response to the scene having changed significantly, initialize parameters for the coding control model; and 
 in response to no significant scene change, update the parameters for the coding control model. 
   
     
     
         11 . The video encoder of  claim 10 , after obtaining the image frame from the video stream, the one or more processors are further configured to access the memory and execute the one or more computer-executable instructions to:
 determine whether the image frame is a first image frame of the video stream; and   in response to the image frame being the first image frame, initialize the parameters for the coding control model.   
     
     
         12 . The video encoder of  claim 10 , after obtaining the image frame from the video stream, the one or more processors are further configured to execute the one or more computer-executable instructions to:
 obtain a target bit rate for the image frame; and   calculate a bits-per-pixel (bpp) rate based on the target bit rate for the image frame.   
     
     
         13 . The video encoder of  claim 10 , wherein:
 the coding control model includes a logarithm rate-quantization model or a quadratic rate-quantization model.   
     
     
         14 . The video encoder of  claim 13 , wherein:
 in the logarithm rate-quantization model, a logarithm function of a target bit rate for the image frame is a linear function of the QP; and   initializing the parameters for the rate control model includes initializing parameters of the linear function.   
     
     
         15 . The video encoder of  claim 14 , wherein:
 updating the parameters for the rate control model includes updating the parameters of the linear function.   
     
     
         16 . The video encoder of  claim 14 , wherein:
 updating the parameters for the rate control model includes updating the parameters of the linear function through a learning rate based on a random gradient decent algorithm.   
     
     
         17 . The video encoder of  claim 16 , wherein:
 the learning rate is pre-configured.   
     
     
         18 . The video encoder of  claim 16 , wherein:
 the learning rate is determined dynamically.   
     
     
         19 . One or more non-transitory computer-readable storage media storing computer-executable instructions that, when executed by a computing system, configure the computing system to perform operations comprising:
 obtaining an image frame from a video stream, wherein the image frame is associated with a coding control model;   encoding the image frame using a quantization parameter (QP) calculated based on the coding control model;   determining whether a scene has changed significantly based on an analysis of the encoded image frame;   in response to the scene having changed significantly, initializing parameters for the coding control model; and   in response to no significant scene change, updating the parameters for the coding control model.   
     
     
         20 . The computer-readable storage media of  claim 19 , wherein the instructions further configure the computing system to perform, after obtaining the image frame from the video stream:
 determining whether the image frame is a first image frame of the video stream; and   in response to the image frame being the first image frame, initializing the parameters for the coding control model.

Join the waitlist — get patent alerts

Track US2022014758A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.