Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Stereo matching method based on segmentation cross trees

A stereo matching and cross-tree technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of poor stability, lack of matching algorithm, and difference in parallax results, etc.

Inactive Publication Date: 2016-07-20
HARBIN NORMAL UNIVERSITY
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, for large areas of weak texture, due to the lack of sufficient and valuable support information, the window-based cost aggregation method will get completely distorted disparity results, and the matching problem of large areas of weak texture has always been based on windows. Difficult Problems for Cost Aggregation Methods
However, the above two algorithms both use the minimum spanning tree as the aggregation strategy. When there are a large number of repeated texture regions in the left and right stereo images, there will be a large number of edges with the same weight in the initial graph structure, so that the structure of the minimum spanning tree is not unique. , choosing different minimum spanning trees will cause a large difference in the final disparity results, resulting in poor stability of the matching algorithm

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 method based on segmentation cross trees
  • Stereo matching method based on segmentation cross trees
  • Stereo matching method based on segmentation cross trees

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045]A stereo matching method based on segmentation cross tree, the method includes six steps, the first step uses Gaussian filter technology to preprocess the left and right stereo images, the second step calculates the initial matching cost, and the third step is each of the left and right stereo images The pixel points to be matched construct a segmentation cross tree. The fourth step uses the one-dimensional integral image acceleration technology to aggregate the initial matching cost in the support area of ​​the segmentation cross tree. The fifth step calculates the disparity according to the "winner takes all" method. The sixth step is based on For the disparity results of the left and right stereo images, the disparity results are corrected by using the left and right consistency detection technology and the weighted median filter technology respectively.

[0046] First, the initial matching cost is calculated according to the pixel gray level information, the gradient ...

Embodiment 2

[0048] In the stereo matching method based on the segmentation cross tree described in embodiment 1, the first step is to perform convolution operation on the original left and right stereo images according to the Gaussian template, and its calculation formula is as follows:

[0049] I ( x , y ) = Σ i = 0 m - 1 Σ j = 0 m - 1 G ( i , j ) * I ′ ( x - i + m - 1 ...

Embodiment 3

[0053] In the stereo matching method based on the segmentation cross tree described in embodiment 1, the second step is to calculate the initial matching cost according to the disparity search range, the gray information of the left and right stereo images, the gradient information of the horizontal and vertical two main directions, and calculate the function To truncate the absolute difference function, the initial matching cost is stored in a 3D disparity space map C raw (x, y, d), its calculation formula is as follows:

[0054] C r a w ( x , y , d ) = ( ...

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 method based on segmentation cross trees, and discloses a stereo matching method based on segmentation cross trees. The method comprises the following six steps: step one, preprocessing left and right stereo images by use of a Gaussian filtering technology, step two, calculating initial matching cost, step three, constructing a segmentation cross tree for each pixel point to be matched of the left and right stereo images, step four, aggregating the initial matching cost in a segmentation cross tree support area by use of a one-dimensional integration image acceleration technology, step five, calculating parallax errors according to a "winner-take-all" method, and step six, according to the parallax error results of the left and right stereo images, correcting the parallax error results respectively by use of a left-right consistency detection technology and a weight median filtering technology. The method provided by the invention is applied to stereo matching based on the segmentation cross trees.

Description

Technical field: [0001] The invention relates to a stereo matching method based on segmented intersection tree. Background technique: [0002] Stereo matching is one of the research hotspots in the field of computer vision. Its purpose is to establish the corresponding relationship between pixels with the same name in two or more images of the same scene, and use the principle of triangulation to reconstruct the three-dimensional information of the scene. This technology is widely used in virtual reality, robot navigation, driverless navigation and other fields. So far, scholars have proposed a large number of methods to solve the matching problem of stereo images. According to different disparity selection methods, stereo matching methods are mainly divided into two categories: global stereo matching methods and local stereo matching methods. The global stereo matching method selects the disparity through global energy minimization, while the local stereo matching method ...

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): G06T7/00
CPCG06T2207/10012G06T2207/20032G06T2207/20228
Inventor 马宁白丽娜
Owner HARBIN NORMAL UNIVERSITY
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
Eureka Blog
Learn More
PatSnap group products