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

An image extraction method based on time information

An extraction method and time information technology, applied in image communication, color TV parts, TV system parts, etc., can solve the problems of greenish foreground, no green parts in the foreground, and high requirements for background curtains, etc., to achieve smoothness There is no requirement for the degree, the effect of saving economic costs and reducing requirements

Active Publication Date: 2019-06-25
BEIJING FILM ACAD
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to overcome the technical defects of the existing image extraction technology that the foreground is greenish caused by diffuse reflection, the foreground cannot contain green parts, and the technical defects of the background curtain are high, and an image extraction method based on time information is proposed. , by setting the shooting frequency of the camera to be the same as the flickering frequency of the light, assign a fixed flickering frequency mark to the non-interest area, and collect image sequences with bright and dark intervals; then use continuous wavelet transform to extract the frequency of brightness change over time between different areas information; finally, different regions can be distinguished according to their frequencies

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
  • An image extraction method based on time information
  • An image extraction method based on time information
  • An image extraction method based on time information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] figure 1 It is a flowchart of an image extraction method based on time information in the present invention. figure 2 is a schematic diagram of Step 1 of an image extraction method based on time information in the present invention. The specific implementation of the present application in a specific application scenario is described according to the above flow chart.

[0041] A. If figure 2 As shown, the light should be placed after the area of ​​interest and before the area of ​​non-interest, and the light should have the characteristics of fast brightening and fast dimming. Use the synchronizer to set the flickering frequency of the light to be the same as the shooting frequency of the camera, and collect image sequences with bright and dark intervals, such as image 3 shown. And shoot at a shooting frequency of not less than 48 frames per second. For ordinary dialogue and slow-moving shots, you can shoot at 96 frames per second; for sports shots, you can shoot...

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 an image extraction method based on time information, and belongs to the technical fields of computer image processing, film and television effects and image matting. The method comprises the following steps: setting the shooting frequency of a camera to be the same as the light flickering frequency, endowing a non-interested area with a mark with fixed flickering frequency, and acquiring an image sequence of bright and dark intervals; extracting frequency information of brightness changing along with time between different areas by using continuous wavelet transform;And finally, different regions can be distinguished according to different frequencies. According to the method, the problem that in a traditional green curtain (blue) image matting process, due to diffuse reflection of a green (blue) curtain, the foreground is greener (bluer) is solved; The problem that the foreground cannot contain a green (blue) part is improved, so that the color expression range of the foreground is not limited; Requirements on the background are reduced, requirements on reflectivity and flatness of the background are avoided, and economic cost is saved.

Description

technical field [0001] The invention relates to an image extraction method based on time information, and belongs to the field of computer image processing, film and television special effects and keying technology fields. Background technique [0002] Image extraction technology refers to extracting a certain area of ​​interest to a user from a digital image, which is a classic problem in the field of computer image processing and film and television special effects. In order to obtain a higher extraction quality, a mark is generally added to the non-interest region when shooting, and the mark is used to separate the interest region from the non-interest region. The image extraction technology (keying technology) in the traditional film and television industry is mainly based on space-based chroma keying. This method adds different color markers to non-interest regions. The usual way to achieve this is to place the subject in front of a special green (blue) flat screen, a...

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): H04N5/272H04N5/232H04N5/235H04N5/04
Inventor 孙略顾晓娟杜鑫张仁杰卢柏宏
Owner BEIJING FILM ACAD