Unlock instant, AI-driven research and patent intelligence for your innovation.

Multifunctional video fast coding method based on deep neural network

A deep neural network and fast coding technology, which is applied in the field of multi-functional video fast coding based on deep neural network, can solve problems such as incompleteness, achieve a wide range of application scenarios, and reduce the effect of coding time

Active Publication Date: 2020-06-09
FUZHOU UNIV
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current intra-frame fast coding algorithm suitable for VVC is not perfect enough.

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
  • Multifunctional video fast coding method based on deep neural network
  • Multifunctional video fast coding method based on deep neural network
  • Multifunctional video fast coding method based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The technical solution of the present invention will be specifically described below in conjunction with the accompanying drawings.

[0041] The present invention provides a kind of multifunctional video fast encoding method based on deep neural network, comprising the following steps:

[0042] Step S1, judging whether the number of reference depth units reaches a preset value, if so, execute step S2;

[0043] Step S2. Predict the depth map of the current coding unit CU based on the BP neural network (back propagation neural network), and then determine the division depth of the CU according to the depth map information;

[0044] Step S3. Based on the probability model, count the ratio of the number of times of the best coded CU partition mode, and determine the prediction sequence of the current CU partition mode according to the probability from large to small;

[0045] Step S4, calculating the rate-distortion RD cost value and according to the corresponding cost jud...

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 relates to a multifunctional video fast coding method based on a deep neural network. The method comprises the steps of firstly, predicting the division depth of a CU by using a back propagation (BP) neural network through researching the time-space domain correlation of video contents; secondly, selecting a division mode of the CU by using the statistical probability; and finally, skipping an unnecessary division mode during encoding so as to save encoding time, thereby achieving the purpose of reducing time complexity under the condition of ensuring that the encoding performance of an encoder is not changed.

Description

technical field [0001] The invention belongs to the technical field of video coding, and in particular relates to a multifunctional fast video coding method based on a deep neural network, so as to achieve the purpose of greatly saving coding time without affecting the coding performance of a coder. Background technique [0002] The new-generation Versatile Video Coding Standard (VVC) adopts more technologies to increase the compression rate to solve the conflict between the rapidly increasing video data and the limited bandwidth network transmission environment. However, while improving the coding efficiency, it also increases the computational complexity of the coding. In the VVC encoding process, video images are divided into blocks (coding units (CU)) of different sizes according to content characteristics to improve compression efficiency, and determining the optimal block method of video images will consume a lot of encoding time. Therefore, if the division process of...

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): H04N19/103H04N19/567H04N19/85G06N3/04G06N3/08
CPCH04N19/103H04N19/567H04N19/85G06N3/084G06N3/045
Inventor 赵铁松王楷徐艺文吴陆狄郑权斐
Owner FUZHOU UNIV