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

A method and device for removing background images

A technology of background image and target image, applied in the field of image processing, can solve the problems of manual intervention, large amount of calculation, inability to process images, etc.

Active Publication Date: 2020-04-07
SHENZHEN AOTO ELECTRONICS
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the image cutting algorithm needs to use energy optimization algorithm and related technologies of graph theory to manually mark the background and target of the picture, and iteratively generate an image with the background removed. This method is difficult, computationally intensive, and requires manual intervention.
Although the method based on seed growth can automatically extract the target image by computer, this method is only suitable for solid-color backgrounds, and cannot handle images with complex backgrounds, and cannot remove the background surrounded by the target image.

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 method and device for removing background images
  • A method and device for removing background images
  • A method and device for removing background images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] figure 1 The implementation process of the method for removing background images provided by the first embodiment of the present invention is shown, and the implementation process is described in detail as follows:

[0028] In step S101, N cameras are turned on at the same time for shooting, and N segments of videos captured by the N cameras are acquired. Each segment of the video includes multiple non-target image frames and multiple target image frames, where N is greater than zero. Integer

[0029] Preferably, N is 4.

[0030] In the embodiment of the present invention, the N cameras simultaneously start shooting the same target object and end shooting at the same time, that is, the N segments of videos captured by the N cameras have the same time.

[0031] In the embodiment of the present invention, the N cameras shoot the same target object, and each video includes multiple non-target image frames and multiple target image frames. The non-target image frames include backgr...

Embodiment 2

[0044] Figure 5 The implementation process of the method for removing background images provided in the second embodiment of the present invention is shown, and the implementation process is described in detail as follows:

[0045] In step S501, aim N cameras at different angles at the same target object, and adjust the parameters of the N cameras so that the parameters of the N cameras are the same;

[0046] In the embodiment of the present invention, the parameters of the N cameras include but are not limited to focal length, aperture, etc. The position of the target object is the center point.

[0047] In the embodiment of the present invention, N cameras are set up at different angles of the target object, and images of the target object at different angles can be obtained when shooting.

[0048] In step S502, the N cameras are turned on at the same time for shooting, and N segments of videos captured by the N cameras are acquired. Each segment of the video includes multiple non-...

Embodiment 3

[0071] Image 6 It shows a schematic diagram of the composition of the background image removing device provided in the third embodiment of the present invention. For ease of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

[0072] The activation module 61 is configured to simultaneously activate N cameras for shooting, and obtain N segments of videos captured by the N cameras, each segment of video includes multiple frames of targetless image frames and multiple target image frames, where N is greater than Zero integer

[0073] The selection module 62 is configured to select M untargeted image frames from each video, and use the M untargeted image frames as the contrast image frame of the corresponding video, where M is an integer greater than zero;

[0074] The calculation module 63 is configured to calculate the difference between the pixel value of the pixel in each target image frame of each video and the ...

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 belongs to the technical field of image processing and provides a method and device for removing background images. The method includes: turning on N cameras for shooting at the same time, and obtaining N segments of video captured by the N cameras. Each segment of the video includes multiple frames of target-free image frames and multiple frames of target image frames; selecting M frames of target-free images from each segment of video. Target image frame, and use M frames without target image frames as the comparison image frames of the corresponding video; calculate the pixel value of the pixel point in each target image frame in each video and the pixel point at the corresponding position in the comparison image frame of the corresponding video The difference in pixel values. If the absolute value of the difference is within the preset pixel value threshold, then the pixel value of the pixel in the target image frame corresponding to the difference is set to a specific value to remove the background in the target image frame. Image; obtain the holographic display video of the N segments of video based on the N segments of video with the background image removed from the target image frame. The invention can automatically extract target images under complex backgrounds.

Description

Technical field [0001] The present invention belongs to the technical field of image processing, and particularly relates to a method and device for removing background images. Background technique [0002] The holographic video is usually an image of a target object with a black background. When shooting the target object, a certain background is attached, which affects the 3D display effect of the video. In the prior art, an image cutting algorithm and a seed-based growth method are usually used to remove the background image in the target object image. However, the image cutting algorithm requires the use of energy optimization algorithms and graph theory related technologies to manually label the background and target of the picture, and iteratively generate images that remove the background. This method is difficult, computationally intensive, and requires manual intervention. . Although the seed-based growth method can automatically extract the target image by a computer...

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): G06T3/00
CPCG06T3/04
Inventor 杨四化李选中吴振志吴涵渠
Owner SHENZHEN AOTO ELECTRONICS