Super-resolution stereoscopic image construction method based on depth perception enhancement

A low-resolution image and high-resolution image technology, applied in the field of building high-definition stereoscopic images, can solve the problems of poor quality of high-definition stereoscopic images, achieve the effect of suppressing noise and enhancing the sense of depth

Active Publication Date: 2019-02-15
ZHEJIANG UNIV OF TECH
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The super-resolution reconstruction of images and the construction of stereoscopic images have been considered and developed separately for a long time. There will be mutual influence between the two technologies, resulting in poor quality of the constructed high-definition stereoscopic 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
  • Super-resolution stereoscopic image construction method based on depth perception enhancement
  • Super-resolution stereoscopic image construction method based on depth perception enhancement
  • Super-resolution stereoscopic image construction method based on depth perception enhancement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.

[0033] A method for constructing a super-resolution stereoscopic image with enhanced depth perception, comprising the following steps:

[0034] 1. Divide the hierarchical area of ​​the image;

[0035] In order to improve the layering of the generated super-resolution stereo image, for the low-resolution image, the image is divided into three parts: close-range, middle-ground and long-range, as follows:

[0036] Analyze and calculate the depth map to obtain the threshold d for the division of the foreground and the middle ground near , the threshold d for midground and foreground division far . The threshold calculation formula is as follows:

[0037]

[0038]

[0039] Among them, d max is the maximum gray value in the depth map, d min is the minimum gray value in the depth map, is the average gray value of the depth map, α repres...

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 a super-resolution stereoscopic image construction method for depth perception enhancement, comprising the following steps: 1. Dividing a hierarchical region of the image; 2,reconstructing a multi-level super-resolution based on a sparse representation; Step 3. Building a high-resolution stereoscopic image. The invention combines two processes of super-resolution reconstruction and stereoscopic construction, and can effectively suppress noise points. In order to enhance the depth perception of stereoscopic images, different depth levels of image blocks are reconstructed with different fineness of super-resolution.

Description

technical field [0001] The invention relates to a method for constructing high-definition stereoscopic images. Background technique [0002] With the rapid development of stereoscopic display technology, people's demand for high-definition stereoscopic images and videos is increasing. The cost of directly capturing 3D images is relatively high, and reconstruction from 2D images is a common way to obtain stereoscopic images. Secondly, in the existing image resources, the resolution of many images is relatively low, and the quality often cannot meet people's requirements. Therefore, the main purpose of the present invention is to reconstruct a low-resolution two-dimensional image into a high-resolution stereoscopic image. [0003] Super-resolution reconstruction is a technology that uses signal processing and image processing methods to convert existing low-resolution images into high-resolution images through algorithms. The super-resolution reconstruction of images and th...

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): G06T3/00G06T3/40G06T7/50G06T7/90G06T17/00
CPCG06T3/0093G06T3/4007G06T3/4053G06T7/50G06T7/90G06T17/00
Inventor 董天阳杨丽锦陈东方
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap