Local stereo matching method based on region base matching

A stereo matching and regional technology, applied in image data processing, instrumentation, computing, etc., can solve the problems of low accuracy and low timeliness of the global method

Active Publication Date: 2019-05-10
SOUTH CHINA AGRI UNIV
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art, provide a local stereo matching method based on region-based matching that can solve the problems of low timeliness of the global method and low accuracy of the local method when the picture is discontinuous, and propose an elastic matching method The method of using the scale space of the image to perform coarse-to-fine image matching

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
  • Local stereo matching method based on region base matching
  • Local stereo matching method based on region base matching
  • Local stereo matching method based on region base matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0079] The present invention will be further described below in conjunction with specific embodiment:

[0080] See attached figure 1 As shown, a local stereo matching method based on region-based matching described in this embodiment includes the following steps:

[0081] S1: Use the binocular stereo acquisition system to acquire a pair of RGB color images of the same size;

[0082] S2: Transform the obtained image:

[0083] The left and right images collected by the binocular camera are rotated and cropped consistently to remove unnecessary parts.

[0084] S3: Calculate the matching cost of the pixel pair, the specific calculation method is as follows:

[0085] In order to reach the reference image block P indexed by (i,j) r (i,j) and test image patch P t The best match of (i, j) needs to determine its relative offset, so a standard is needed to measure their similarity or correlation coefficient C rt ;

[0086] For the convenience and accuracy of calculation, the vect...

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 local stereo matching method based on region base matching. The method comprises the following steps: S1, obtaining a pair of images by using a binocular stereo acquisitionsystem; s2, transforming the acquired image; s3, calculating the matching cost of the pixel pair; s4, performing cost value aggregation on the matching cost in the step S3; s5, on the basis of the step S4, performing local optimization to obtain a disparity map; s6, carrying out post-processing on the disparity map obtained in the step S5; and S7, carrying out matching inspection on the disparitymap processed in the step S6. Based on region base matching, the problems that the global method is low in timeliness and the local method is low in accuracy when pictures are discontinuous are solved.

Description

technical field [0001] The invention relates to the technical field of digital image processing and computer vision, in particular to a local stereo matching method based on region-based matching. Background technique [0002] Stereo matching is a key method for extracting three-dimensional environment information from two images of a scene obtained at the same time from slightly different positions based on a binocular stereo acquisition system. Grouping stereo matching methods hierarchically can be divided into: local methods and global methods. Local methods include feature matching and region matching; global methods include belief propagation, dynamic programming, graph cut method, nonlinear diffusion, scale space method, and tensor voting method. The global method uses all cost values ​​to determine the disparity value and occlusion during the optimization process, and many of the global methods use the local method to calculate the disparity map, so there is a connec...

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): G06T7/593
CPCY02T10/40
Inventor 赵祚喜赖琪何振宇徐伟诚马昆鹏蒙劭洋
Owner SOUTH CHINA AGRI UNIV
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap