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

A fast scene switching detection method and system

A technology of scene switching and detection method, applied in the field of image processing, can solve problems such as low algorithm efficiency

Active Publication Date: 2021-02-26
深圳市梦网视讯有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the embodiments of the present invention is to propose a fast scene switching detection method, aiming to solve the problem of low efficiency of the algorithm by performing full-frame image analysis on images that have not been switched in the prior art

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
  • A fast scene switching detection method and system
  • A fast scene switching detection method and system
  • A fast scene switching detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] figure 1 It is a flowchart of a fast scene switching detection method in a preferred embodiment of the present invention; the method includes:

[0034] Step1: if frame cur , frame next If there are unencoded frames in , encode the unencoded frames first, and then enter Step2; otherwise, directly enter Step2.

[0035] Step2: If pocn ext - poc cur ≤Thres 1 , go to Step4; otherwise, go to Step3.

[0036] Among them, frame cur , frame next respectively represent the current frame and the next frame of the current frame in the encoding order; poc cur 、poc next represent frame respectively cur , frame next The playback sequence number; Thres 1 Indicates the first threshold threshold, generally Thres 1 >2.

[0037] Step3: If Then determine the frame next Switch frames for the scene, let frame cur = frame next and update the frame next , and then re-enter Step1; otherwise, enter Step4.

[0038] in, Indicates frame next Contains the number of intra predic...

Embodiment 2

[0073] Figure 4 It is a structural diagram of a rapid scene switching detection system in a preferred embodiment of the present invention; the system includes:

[0074] Uncoded frame detection processing module, used to judge if frame cur , frame next If there is an unencoded frame, first encode the unencoded frame, and then enter the frame interval threshold judgment processing module; otherwise, directly enter the frame interval threshold judgment processing module.

[0075] The frame interval threshold judgment processing module is used to judge if poc next - poc cur ≤Thres 1 , then enter the scene time span variable acquisition module; otherwise, enter the intra prediction block number threshold judgment processing module.

[0076] Among them, frame cur , frame next respectively represent the current frame and the next frame of the current frame in the encoding order; poc cur 、poc next represent frame respectively cur , frame next The playback sequence number; ...

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 proposes a fast scene switching detection method and system. On the one hand, the method of the present invention adaptively determines the length of the scene analysis time window through the analysis of the motion intensity of the object in the image; and then uses the time window as a unit to periodically detect the scene switching. On the other hand, according to the scene change characteristics of the background area at the top of the image, the determination of non-switching frames can be cut off in advance. In this way, while ensuring the accuracy of scene detection, at the same time, unnecessary waste of calculation in traditional frame-by-frame and full-frame detection algorithms is avoided, thereby achieving the purpose of improving algorithm efficiency.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a fast scene switching detection method and system. Background technique [0002] Actual video sources are diverse, and precise scene switching can improve the compression performance of the encoder. However, from the perspective of time domain, although the traditional frame-by-frame analysis method is more accurate in judgment, the probability of scene switching frame by frame is actually extremely low; from the perspective of space domain, the traditional full-frame analysis method has high accuracy. However, the characteristics of the foreground and background of different scenes are ignored, and full-frame image analysis is also performed on images that have not been switched, which will also lead to low algorithm efficiency. Contents of the invention [0003] The purpose of the embodiments of the present invention is to propose a fast scene switching detection method, aim...

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 Patents(China)
IPC IPC(8): H04N19/142H04N19/179H04N19/87
CPCH04N19/142H04N19/179H04N19/87
Inventor 舒倩
Owner 深圳市梦网视讯有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More