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

2D-to-3D conversion method based on image edge information

An image edge, 3D technology, applied in image communication, electrical components, stereo systems, etc., can solve problems such as inability to meet 3D images, and achieve the effect of reducing costs and costs

Inactive Publication Date: 2012-04-04
SUN YAT SEN UNIV
View PDF5 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, a large number of existing image capture devices can only collect 2D images, which cannot meet people's needs for 3D images. Generally, 2D images are captured from stereoscopic scenes, and a lot of information contained in the images can be used as clues. To reconstruct the original 3D scene, which makes it possible to convert 2D images into 3D images

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
  • 2D-to-3D conversion method based on image edge information
  • 2D-to-3D conversion method based on image edge information
  • 2D-to-3D conversion method based on image edge information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be further elaborated below in conjunction with the accompanying drawings.

[0039] like figure 1 and figure 2 As shown, the method flow of the present invention based on image edge information from 2D to 3D includes:

[0040] 1) Perform color space conversion on the original 2D image, convert from RGB space to YUV space, and extract brightness components for subsequent processing. Convert from RGB space to YUV space, using the following formula:

[0041] Y=0.299R+0.587G+0.114B

[0042] U=-0.1687R-0.3313G+0.5B+128

[0043] V=0.5R-0.4187G-0.0813B+128

[0044] 2) Denoise the brightness image: Since the image will inevitably be affected by noise during the process of acquisition and transmission, it is necessary to denoise the image for subsequent effective processing, and the Gaussian filter is widely used to denoise the image. noise filter. Because the noise is generally concentrated in high frequencies, and the two-dimensional Gaussian...

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 discloses a 2D-to-3D conversion method based on image edge information which has better image processing effect and is applicable to various types of output manners, comprising the following steps of: 1) carrying out color space conversion to an original 2D image so as to convert an RGB space into a YUV space, and extracting an image brightness component; 2) carrying out denoising filter process to the brightness image by an isotropic 2D Gauss filter; 3) carrying out Canny edge detection to the denoised brightness image to extract image edge information; 4) generating a vertical depth map and a horizontal depth map or a total depth map by adopting a strip division method; 5) mapping each pixel of the original image to a new position from the original position according to the vertical depth map and the horizontal depth map or the total depth map so as to obtain a new image; and 6) taking the new image and the original image as a left eye image and a right eye image of human respectively, selecting a proper composition manner according to the output manner, and outputting a 3D image after the composition of the left eye image and the right eye image.

Description

technical field [0001] The present invention relates to the technical fields of video processing and image processing, in particular, to a method for converting 2D to 3D based on image edge information. Background technique [0002] Today, as a new generation of visual technology revolution, 3D images have penetrated into various fields, not only promoting the development of related technologies, but also improving people's quality of life and bringing great changes to people's lives. 3D images are more advanced than 2D images. It is more realistic and expressive, giving people a strong visual shock, so that people are no longer satisfied with the plainness of 2D images. [0003] However, a large number of existing image capture devices can only collect 2D images, which cannot meet people's needs for 3D images. Generally, 2D images are captured from stereoscopic scenes, and a lot of information contained in the images can be used as clues. To reconstruct the original 3D sce...

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): H04N13/00H04N15/00
Inventor 庞志勇陈弟虎江嘉文雷东玮范锡添
Owner SUN YAT SEN UNIV