Check patentability & draft patents in minutes with Patsnap Eureka AI!

A Disparity Map Refinement Method Based on Markov Random Field

A technology of Markov random field and disparity map, which is applied in the field of computer vision and pattern recognition, can solve problems such as there is no very effective solution, and achieve the effect of improving accuracy

Active Publication Date: 2018-02-06
LANZHOU UNIVERSITY OF TECHNOLOGY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

How to "eliminate" these outliers in the disparity map, there is currently no very effective solution

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 Disparity Map Refinement Method Based on Markov Random Field
  • A Disparity Map Refinement Method Based on Markov Random Field
  • A Disparity Map Refinement Method Based on Markov Random Field

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] The refinement method of disparity map based on Markov random field of the present invention comprises the following steps:

[0049] (1) Read the initial left disparity map. The initial left disparity map is obtained by a certain stereo matching algorithm. For example, a global stereo matching algorithm such as trust propagation algorithm, graph cut algorithm, etc. can be used;

[0050] (2) Generate the right disparity map, and use the left and right correspondence principle of stereo matching, that is, the corresponding right disparity map can be generated according to the left disparity map;

[0051] (3) Abnormal parallax point detection;

[0052] (4) Classification of disparity points, which divides all disparity points in the initial disparity map into three categories;

[0053] (5) Establish a Markov random field model;

[0054] (6) Establish the global energy equation;

[0055] (7) Calculate the data item and smoothing item, and the data item is calculated by c...

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

A method for refining a disparity map based on a Markov random field belongs to the technical field of computer vision and pattern recognition. The steps are as follows: input an initial left disparity map to obtain a right disparity map; use an extended cross-validation method to detect abnormal points And classify the disparity points; establish the global energy function; calculate the data item and the smoothing item; use the graph cut algorithm to solve; get the refined disparity map. This method can effectively remove the mismatching points in the disparity map generated by the local or global stereo matching algorithm, greatly improve the accuracy of the disparity map, and finally obtain a refined high-precision disparity map, which is beneficial to the further processing of visual depth information.

Description

technical field [0001] The invention relates to the fields of computer vision and pattern recognition, in particular to a method for refining a disparity map in stereo vision technology. Background technique [0002] The stereo matching problem is a key scientific problem in computer vision, and there is no completely satisfactory solution so far. Many algorithms trade off matching efficiency and accuracy for different applications. Here we only discuss how to further improve the accuracy of stereo matching. [0003] Given two corrected stereo image pairs, when a certain algorithm is used to solve the stereo matching problem, the result of the algorithm is often a left disparity map or two left and right disparity maps. Due to the influence of various complex factors such as occlusion, there are always more or less mismatches in the obtained disparity map. These mismatches are represented by many outliers in the disparity map, and some outliers are even Large area. This ...

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): G06T7/30
CPCG06T2207/20228
Inventor 何俊学
Owner LANZHOU UNIVERSITY OF TECHNOLOGY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com