Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Intelligent video compression method and device based on optical flow decision

A technology of video compression and optical flow energy, applied in digital video signal modification, image communication, electrical components, etc., can solve the problems of increasing optical flow data volume, not optimal optical flow, increasing the number of stored motion information bits, etc.

Active Publication Date: 2021-04-23
SHENZHEN UNIV
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, precise optical flow is often not optimal for specific video tasks
In addition, compared with the motion information in traditional compression systems, the data volume of optical flow increases significantly, directly applying existing compression methods to compress optical flow values ​​will significantly increase the number of bits required to store motion information

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
  • Intelligent video compression method and device based on optical flow decision
  • Intelligent video compression method and device based on optical flow decision
  • Intelligent video compression method and device based on optical flow decision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] see Figure 1 to Figure 5 , an intelligent video compression method based on optical flow decision-making, including:

[0068] S1. Perform multi-scale downsampling on the nth frame of video f(n), input the downsampling results of all scales into a scene analysis network, and obtain the current frame f through the semantic-based optical flow energy intensity calculation formula n A panoptic semantic segmentation expression {∑ type ∑ group p(i, j)}, where p(i, j) marks the coordinates of an element in a pixel group group of a certain category type as (i, j), and the semantic-based optical flow energy intensity calculation formula for:

[0069]

[0070]

[0071] where v i，j (n) is the speed of pixel point p(i, j) in the nth frame at the current scale, K is the number of scales for multi-scale downsampling, DS k is the downsampling factor coefficient at scale k, H×W is the frame size of the input video, mean( ) means taking the average value, experimental, ε n ...

Embodiment 2

[0111] The present invention also relates to an intelligent video compression device based on optical flow decision-making, including an acquisition module, a judgment module and a processing module,

[0112] Multi-scale downsampling is performed on the nth frame of video f(n), and the downsampling results of all scales are input into a scene analysis network. The acquisition module can obtain the current frame f through the semantic-based optical flow energy intensity calculation formula n A panoptic semantic segmentation expression {∑ type ∑ group p(i, j)}, where p(i, j) marks the coordinates of an element in a pixel group group of a certain category type as (i, j), and the semantic-based optical flow energy intensity calculation formula for:

[0113]

[0114]

[0115] where v i，j (n) is the speed of pixel point p(i, j) in the nth frame at the current scale, K is the number of scales for multi-scale downsampling, DS k is the downsampling factor coefficient at scal...

Embodiment 3

[0134] The present invention also relates to a computer device, including a memory, a processor, and a computer program stored in the memory and operable on the processor, characterized in that: when the processor executes the computer program, any one of the above-mentioned steps of the method described above.

[0135] When the processor executes the computer program, the steps in the foregoing method embodiments are realized. Alternatively, when the processor executes the computer program, the functions of the modules or units in the above device embodiments are implemented.

[0136] Exemplarily, the computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of accomplishing specific functions, and the instruction segments are used to describe the execut...

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 an intelligent video compression method and device based on optical flow decision. The method comprises the following steps: acquiring panoramic semantic segmentation expression of a current frame; judging whether the current frame is a key frame or not: if so, obtaining the optical flow energy intensity of the current frame; obtaining the score of an optical flow energy threshold OPET; and judging whether the optical flow energy intensity is greater than the score of an optical flow energy threshold OPET or not: if so, carrying out quantization processing on the image characteristics of the current frame by adopting a high bit number. The invention has the beneficial effects that according to the time continuity and the space consistency of the optical flow, the scene analysis technology is utilized to reserve full resolution of frames related to stronger motion information in the video frame group, and the part with less information amount is transmitted in a feature extraction mode after down-sampling, so the transmission data volume is effectively reduced; by extracting the reconstruction error information and returning the reconstruction error information to the video frame, the texture information is better reserved in the reconstruction process, and better bit rate- distortion optimization of the video compression system is realized.

Description

technical field [0001] The invention relates to the technical field of video compression, in particular to an intelligent video compression method and device based on optical flow decision-making. Background technique [0002] With the development of the Internet, video content has accounted for more than 80% of traffic in today's era, and it is expected that this proportion may be further increased in the future. In addition, most computer vision tasks require very high video compression quality when applied to real-world scenarios. Efficient video compression methods can provide great convenience for the deployment and implementation of computer vision tasks. It can be seen that it is critical and urgent to establish a high-efficiency video compression system to transmit high-quality video under a predetermined bandwidth budget. [0003] The traditional video compression method adopts the predictive coding structure to encode the corresponding motion information and resi...

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
Patent Type & Authority Applications(China)
IPC IPC(8): H04N19/42H04N19/70H04N19/136H04N19/147H04N19/137
Inventor 王妙辉许倬维
Owner SHENZHEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com