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

Stereo Matching Algorithm Based on Fusion of Spearman Correlation Coefficient and Dynamic Programming

A correlation coefficient and dynamic programming technology, applied in the field of computer vision, can solve the problems of low precision of local algorithms and poor real-time performance of global algorithms, and achieve the effect of precise precision

Active Publication Date: 2021-04-30
UNIV OF SHANGHAI FOR SCI & TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention aims at the problems of low accuracy of local algorithms in specific areas and poor real-time performance of global algorithms, and proposes a stereo matching algorithm based on the fusion of Spearman correlation coefficient and dynamic programming, using Spearman correlation coefficient to calculate the matching cost, Introducing the Spearman correlation coefficient to find the matching cost is more suitable for special image areas such as illumination radiation

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
  • Stereo Matching Algorithm Based on Fusion of Spearman Correlation Coefficient and Dynamic Programming
  • Stereo Matching Algorithm Based on Fusion of Spearman Correlation Coefficient and Dynamic Programming
  • Stereo Matching Algorithm Based on Fusion of Spearman Correlation Coefficient and Dynamic Programming

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] Such as figure 1 The flow chart of the stereo matching algorithm based on Spearman correlation coefficient and dynamic programming fusion is shown, and the specific steps of the algorithm are as follows:

[0025] The first step is to read the left and right corrected pictures from the binocular stereo camera. For any reference point p(x, y) in the left picture, there is a corresponding point q(x-d, y), then the matching cost e(x, y, d) of p and q can be expressed as:

[0026] e(x,y,d)=min{|I L (x,y)-I R (x-d,y)|,T},

[0027] where d ∈ (0, d max ), d max is the maximum parallax, I L (x, y) is the pixel value of p(x, y) in the left image, I R (x-d, y) is the pixel value of q(x-d, y) in the right image, and T is the pixel threshold. so that d max +1 matching cost map.

[0028] The second step, cost aggregation:

[0029] Use 3*3 windows for cost aggregation for each matching cost map, and the matching cost after aggregation is where e(X, Y, d), C 1 (x, y, d) a...

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 stereo matching algorithm based on the fusion of Spearman correlation coefficient and dynamic programming. The Spearman correlation coefficient is used to calculate the matching cost, and the Spearman correlation coefficient is introduced to calculate the matching cost, which is more suitable for special image areas with illumination radiation and the like. Then an energy model is established for each pixel, that is, an energy model is established by fusing multiple matching costs, and the energy model is optimized through dynamic programming to obtain candidate disparity values. This kind of model combines multiple matching costs, which can improve the matching accuracy of a single matching cost. For example, edge information can be better preserved by fusing pixel difference and gradient information. Solve the problem that it is difficult to accurately match special image areas such as illumination and radiation; solve the problem of insufficient matching accuracy of a single matching cost in some special areas; average the candidate disparity values ​​to obtain the final disparity value, so that the obtained disparity The value precision is accurate to decimals.

Description

technical field [0001] The invention relates to a computer vision technology, in particular to a stereo matching algorithm based on Spearman correlation coefficient calculation matching cost and dynamic programming fusion. Background technique [0002] Stereo vision is a vital branch of the field of computer vision. It is a method of simulating the principle of human vision and using a computer to passively perceive distance. Observe an object from two or more points, obtain images under different viewing angles, find matching points according to the matching relationship between pixels in the images, and obtain the deviation between pixels, and then obtain the depth information of the object through triangulation. [0003] Stereo matching is a key step in stereo vision, and its purpose is to find homologous points in image pairs. In the 1980s, Marr of the Massachusetts Institute of Technology proposed a computer theory and applied it to binocular matching, so that two plan...

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): G06T7/55
CPCG06T2207/10004G06T2207/20021G06T2207/20228G06T7/55
Inventor 于修成王永雄宋燕李航
Owner UNIV OF SHANGHAI FOR SCI & TECH
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