Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Quality Evaluation Method of Binocular Fusion Stereo Image Based on Weighted Gradient Magnitude

A gradient amplitude and stereoscopic image technology, applied in the field of image processing, can solve the problems of left and right image distortion asymmetry, non-structural distortion, etc., and achieve the effect of good structural information and eliminating contrast changes

Active Publication Date: 2020-12-29
HANGZHOU DIANZI UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, different distortion types, left and right image distortion asymmetry, structural distortion and non-structural distortion, etc. will bring certain challenges to the evaluation criteria.

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 Quality Evaluation Method of Binocular Fusion Stereo Image Based on Weighted Gradient Magnitude
  • A Quality Evaluation Method of Binocular Fusion Stereo Image Based on Weighted Gradient Magnitude
  • A Quality Evaluation Method of Binocular Fusion Stereo Image Based on Weighted Gradient Magnitude

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described below in conjunction with drawings and embodiments.

[0036] like figure 1 As shown, the present invention proposes a binocular fusion stereo image quality evaluation method based on weighted gradient magnitude, which specifically includes the following five steps:

[0037] Step 1: Create a gradient monocular map.

[0038] 1-1. Calculate the stereoscopic image CM based on the CSF filtering stage v and the gradient magnitude map GM v , the weighted gradient magnitude map is calculated as follows:

[0039]

[0040] where e is a small positive constant to avoid numerical instability when α(x,y) has small values. v ∈ (L, R), represents the left and right stereo images. α(x, y) can be calculated according to the formula inferred. where CG(x, y) can be calculated according to the formula come out, π x，y is a local window centered on (x, y). ω(x′,y′) is obtained by the formula Satisfy ∑ x′，y′ Positive symmetri...

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 binocular fusion stereo image quality evaluation method based on weighted gradient amplitude. The objective image quality evaluation algorithm can be divided into a full-reference image quality evaluation algorithm, a half-reference image quality evaluation algorithm and a no-reference image quality evaluation algorithm according to whether an original image is utilized to participate in image quality evaluation or not. According to the invention, a semi-reference stereo image objective quality evaluation algorithm is adopted. Different from a traditional algorithm for generating the one-eye diagram by fusing the left eye image and the right eye image, the gradient amplitude factor subjected to local weighting is added into the binocular fusion algorithm, so thatstructural information lost in the traditional one-eye diagram construction process is compensated to a certain extent. The local image structure is enhanced while the contrast change is eliminated. Aclassical self-adaptive sparse dictionary and an OMP iteration algorithm are adopted to capture edge and texture information enhanced along with the increase of iteration times, so that the structureinformation of the image can be better embodied.

Description

technical field [0001] The invention relates to the field of image processing, involves applying a locally weighted gradient magnitude map to simulate retinal cortex information, fusing left and right eyes to obtain a cyclopean map, and reconstructing it with a classic dictionary to obtain information entropy. It is an improvement and optimization of a stereoscopic image objective quality evaluation method. Background technique [0002] Vision is the main way for human beings to experience the world of external organs of the human body. Obtaining high-quality visual experience has been the constant pursuit of people since ancient times. With the development of science and technology in recent years, stereoscopic image quality evaluation has become an important research field in modern image processing technology. However, the complexity of the human visual system has brought a lot of technical obstacles to related research. Binocular vision is not only a simple superpositio...

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): G06T7/60G06T5/50
Inventor 张桦张悦戴国骏沈方瑶赵月周文晖
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com