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

Stereo matching algorithm based on color information and graph-cut theory

A technology of stereo matching and color information, applied in the field of computer vision, can solve the problems of loss of image detail information, low real-time algorithm and low matching accuracy, etc., to shorten the running time, facilitate the implementation, and improve the matching accuracy.

Active Publication Date: 2017-03-22
HUNAN VISION SPLEND PHOTOELECTRIC TECH
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, the stereo matching algorithm based on the SAD area can meet the real-time requirements, but the algorithm is sensitive to noise, and at the same time, the large matching window will cause the loss of image detail information, and the obtained disparity results are in weak texture areas, discontinuous disparity, etc. The matching accuracy in special areas is not high; although the overall matching algorithm based on the global stereo matching algorithm has high overall matching accuracy, the algorithm has low real-time performance

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 color information and graph-cut theory
  • Stereo matching algorithm based on color information and graph-cut theory
  • Stereo matching algorithm based on color information and graph-cut theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] Taking the picture library on the Middlebury website and the pictures taken by the camera as examples, the present invention will be further described in detail in conjunction with the accompanying drawings.

[0052]S1. Under the RGB color model, the initial parallax result is obtained by combining template weights, color difference constraints and the local matching algorithm of SAD;

[0053] S1.1 Under the RGB color model, match template weights and SAD algorithm;

[0054] R, G, B are the three channels of the color image, f QL (x,y) (where Q=R, G, B) is the channel value of the left image, f QR (x, y) (where R, G, B ∈ Q) are the channel values ​​of the right image. Then in the RGB color model, the SAD matching cost of any corresponding pixel in the left and right image pair is:

[0055]

[0056] In the formula, d represents the disparity value of the pixel point (x, y); h and k represent the displacement moving in the x and y directions, respectively.

[0057]...

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 provides a stereo matching algorithm based on color information and graph-cut theory, and relates to the field of computer vision. The method comprises the following steps: to begin with, under an RGB color space model, carrying out matching by combining template weight and an SAD algorithm and judging an SAD optimal matching point by utilizing color difference constraint conditions, thereby enabling SAD initial matching accuracy to be improved, suppressing noise and meanwhile, keeping scene detail information; carrying out occlusion detection by utilizing left-right consistency check criteria, thereby improving matching precision of an initial matching occlusion region; and meanwhile, for the problem of not high matching precision of initial matching textureless regions and parallax discontinuous regions, constructing an energy gird chart and an energy function through a graph-cut algorithm and carrying out global optimization to obtain a high-precision parallax result. The method improves the situations of not high precision of a local stereo matching algorithm and weak real-time performance of a global stereo matching algorithm, improves matching precision of special regions of the discontinuous regions and the like, and reduces algorithm matching time.

Description

technical field [0001] The invention relates to the field of computer vision, specifically referring to a stereo matching algorithm based on color information and graph cut theory. Background technique [0002] Stereo vision is a vital branch of the field of computer vision, widely used in three-dimensional non-contact measurement, architecture, robot vision, aerial surveying and mapping, and military applications, so that it has become one of the hot topics in the world today. [0003] Stereo vision technology mainly includes image acquisition, image preprocessing, camera calibration, stereo correction, stereo matching and three-dimensional reconstruction. Among them, stereo matching is the core part of stereo vision, which directly affects the estimation of subsequent depth information and the effect of 3D reconstruction. Stereo matching aims to obtain the disparity value of the corresponding pixel of the image. According to the sparse and dense rows of the disparity map,...

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): G06T7/30G06T7/593G06T7/162
CPCG06T2207/10012G06T2207/20028G06T2207/20032G06T2207/20072
Inventor 陈蓉宋斌
Owner HUNAN VISION SPLEND PHOTOELECTRIC 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