Hierarchical video code stream coding method and architecture for time division multiplexing neural network processor

A neural network and time-division multiplexing technology, which is applied in digital video signal modification, electrical components, image communication, etc., can solve problems such as insurmountable coding rate, unreasonable video coding structure, and reduced video information quality, and achieve time-division multiplexing. Use, avoid the effect of task burst or data processing load that cannot be shared

Active Publication Date: 2017-01-04
GUANGDONG VIMICRO
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiment of the present invention provides a time-division multiplexing neural network processor video hierarchical code stream encoding method, which solves the technical problem that the existing video encoding technology cannot overcome the encoding rate and cause the quality of video information to decrease
[0006] The e

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Hierarchical video code stream coding method and architecture for time division multiplexing neural network processor
  • Hierarchical video code stream coding method and architecture for time division multiplexing neural network processor

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. The embodiments of the present invention and all other embodiments obtained by persons of ordinary skill in the art without creative efforts all belong to the protection scope of the present invention. The step numbers in the drawings are only used as reference signs for the steps and do not indicate the order of execution.

[0035] like figure 1 As shown, the video hierarchical code stream encoding method of the time-division multiplexing neural network processor in the embodiment of the present invention includes:

[0036] Step 05, the source video is formed into multi-channel synchronous video;

[0037] Step 10, acquire the synchronous video, and for...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a hierarchical video code stream coding method for a time division multiplexing neural network processor. The hierarchical video code stream coding method comprises the following steps: obtaining a synchronous video, and forming a video object in the synchronous video according to a preset analysis model; obtaining the synchronous video, and optimizing the image in the synchronous video according to a preset optimization model to form an optimized video; obtaining the video object, a task processing model and the synchronous video, allocating processing resources to a task processing process of the task processing model by time division multiplexing, and carrying out corresponding task processing on the video object to form corresponding object description information; and carrying out video coding on the optimized video, coding the corresponding object description information, and embedding video code stream to form hierarchical code stream of a source video. The optimized video and the analysis and processing result information of the video objects are synchronously combined in a coding mode, so that the source video forms the hierarchical code stream containing video contents and related information of the video objects. The invention further provides hierarchical video code stream coding architecture for the time division multiplexing neural network processor.

Description

technical field [0001] The present invention relates to a data processing method and processing device, in particular to a display data processing method and processing device. Background technique [0002] Video transmission consumes a lot of bandwidth. In the field of video surveillance, real-time high-definition streams consume the most bandwidth and system processing resources. Therefore, in the prior art, the bandwidth problem is generally solved by encoding and compressing the source video to form a low-rate bit stream suitable for real-time transmission and a high-rate bit stream suitable for delayed transmission. However, only using the code rate to adapt the bandwidth cannot guarantee the real-time and reliable transmission of information in the video. When the code rate is reduced, the quality of information carried in the video is correspondingly reduced or even unusable. It is feasible to use different encoding methods to encode the information in the video and...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): H04N19/132H04N19/146H04N19/174H04N19/33H04N19/167H04N19/423H04N19/436H04N19/30H04N19/85H04N19/80
CPCH04N19/132H04N19/146H04N19/167H04N19/174H04N19/30H04N19/33H04N19/423H04N19/436H04N19/80H04N19/85
Inventor 孙晓伟卢京辉
Owner GUANGDONG VIMICRO
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products