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

Stereo matching algorithm based on four-mode Census transform and discrete parallax search

A technology of stereo matching and parallax, applied in computing, image data processing, instruments, etc., can solve problems such as low efficiency and increased computation

Inactive Publication Date: 2019-03-01
HEFEI UNIV OF TECH
View PDF0 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the input image is a high-resolution image, the computational complexity of the algorithm increases sharply, and the efficiency of processing the input image to obtain the required disparity map is extremely low.

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 four-mode Census transform and discrete parallax search
  • Stereo matching algorithm based on four-mode Census transform and discrete parallax search
  • Stereo matching algorithm based on four-mode Census transform and discrete parallax search

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0149] The stereo matching algorithm based on block matching of the present invention is carried out step by step. Firstly, the input left and right original images are converted into grayscale images as left and right reference images. Then use the four-mode Census transformation to transform the left and right reference images into left and right feature maps, and construct a matching cost for these two feature maps. Combined with the block matching algorithm, the left and right initial disparity maps are iteratively calculated to obtain the coarse disparity map, and the number of iterations is set to 3 times. After the iteration is completed, the final fine disparity map is obtained by using the method of disparity refinement.

[0150] figure 1 It is a schematic flowchart of a stereo matching algorithm based on four-mode Census transform and discrete disparity search according to an embodiment of the present invention. Such as figure 1 The algorithm shown includes the ...

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

Aiming at the shortcomings of the existing technology, a stereo matching algorithm based on four-mode Census transform and discrete parallax search is proposed in this invention, which includes: inputting left and right original images, convert them into left and right gray images, and treating the converted gray images as left and right reference images; constructing the cost volume of left and right reference diagrams to obtain the matching cost of reference diagrams; random generation of left and right initial disparity maps; Using block matching algorithm, the left and right initial disparity maps are iteratively calculated to obtain rough disparity maps. The rough disparity map is optimized to obtain the final fine disparity map and output. Advantageous technical effect: the inventioncan obtain high-quality parallax map, and greatly reduces the calculation amount at the same time. Experiments show that the algorithm has a shorter running time and can get a more accurate disparitymap.

Description

technical field [0001] The invention relates to the field of computer vision stereo matching, in particular to a stereo matching algorithm based on four-mode Census transformation and discrete parallax search. Background technique [0002] In the field of computer vision, the problem of stereo matching (Stereo Matching) is one of the most widely studied and most basic problems. It obtains the disparity map and stereo information of the same target based on multiple pictures of the same target in the real environment. It can be said that stereo vision is an important research hotspot in today's computer, and has been widely used in fields such as human-computer interaction, video surveillance, intelligent control, terrain reconstruction, robot navigation, and object tracking. [0003] At the same time, stereo matching has always been a difficult problem in research, and the core problem of stereo matching is to calculate the disparity image. How to improve the matching accur...

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): G06T7/55G06T7/33
CPCG06T7/337G06T7/55
Inventor 杨依忠徐栋荣燊解光军鲁迎春
Owner HEFEI UNIV OF 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