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

Three-dimensional matching algorithm between adaptive window and weight based on picture edge

An adaptive window and stereo matching technology, applied in the field of computer vision, can solve the problems of complex algorithms and large amount of calculation, and achieve the effect of consistent size and uniform reference value

Active Publication Date: 2013-06-26
NANJING UNIV OF SCI & TECH
View PDF1 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Adaptive weight matching algorithm based on color and space, each pixel in the two windows is assigned a weight value related to the color distance and geometric distance index of the center point of its own window, with the absolute error as the initial matching cost, normalized Weighted calculation of regional correlation, the algorithm has high precision, but the algorithm is complex and the calculation is large

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
  • Three-dimensional matching algorithm between adaptive window and weight based on picture edge
  • Three-dimensional matching algorithm between adaptive window and weight based on picture edge
  • Three-dimensional matching algorithm between adaptive window and weight based on picture edge

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] like figure 2 Shown: a kind of stereo matching algorithm based on the adaptive window of image edge and weight of the present invention, comprises the following steps:

[0029] Step 1: Use the Canny operator to find the edge of the reference image;

[0030] Step 2: Step 2, point-by-point detection, according to whether it is an edge and the strength of the edge, assign different neighborhood window sizes, and select three neighborhood window sizes M, N, O (M>N>O); then Detect the edge of the image, based on this, if the center of the window is on the strong edge, then set the size of the support window to O, if the center of the window is on the weak edge, then set the size of the window to N, otherwise set the size of the window to M; The weight distribution model of the geometric distance from the domain point to the window center, as shown in formula (1),

[0031] fw ( i , j ) ...

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 three-dimensional matching algorithm between an adaptive window and a weight based on a picture edge. The algorithm comprises the following steps of: firstly, rapidly and dynamically selecting a window supporting size by picture edge information; providing a weight model which accords with a probability curve according to the characteristic that a matching value is changed along the geometrical distance from a neighborhood point to the center of the window; and combining with the color similarity constraint, wherein the weighted color distance cumulative sum is the similarity quantity, and computing parallax errors by points to obtain a dense disparity map. After the algorithm is used, matching noise can be effectively reduced, the matching precision between a high-edge region and a low-texture region can be improved, and the rapid and high-efficiency three-dimensional matching can be realized.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to a stereo matching algorithm based on image edge adaptive window and weight. Background technique [0002] Binocular stereo vision is a computer vision system that obtains three-dimensional information of a scene by imitating the characteristics of human binocular vision. The binocular camera obtains scene information from different angles, calculates the distance from the corresponding point to the imaging surface according to the parallax, and obtains depth perception and 3D reconstruction. Binocular stereo matching algorithm has always been a hot research topic. [0003] Currently, widely researched stereo matching algorithms are mainly divided into three categories: feature point-based matching algorithms, region-based matching algorithms and global-based matching algorithms. [0004] The matching algorithm based on feature points is a matching algorithm based on features such...

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): G06T7/00
Inventor 柏连发张毅陈钱顾国华岳江韩静荆鑫万一龙
Owner NANJING UNIV OF 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