Stereo matching method based on neighborhood related information

A technology of stereo matching and neighborhood correlation, which is applied in image data processing, instrumentation, computing, etc., can solve problems such as image noise and brightness sensitivity, high algorithm complexity, and wrong matching, so as to improve accuracy and robustness, overcome Mis-match, improve the effect of mis-match

Pending Publication Date: 2019-11-19
TIANJIN UNIV
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, stereo matching is the key technology of stereo vision. Its algorithm is complex and needs to process a large amount of data. At present, there is no general algorithm that can meet the requirements of most scenes.
[0003] Among many matching algorithms, the AD algorithm is based on the gray value of the pixel, that is, it is assumed that the same feature point of the two images has the same gray valu

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 neighborhood related information
  • Stereo matching method based on neighborhood related information
  • Stereo matching method based on neighborhood related information

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0032] The technical scheme of the present invention is detailed as follows:

[0033] (1) Improved Census algorithm based on neighborhood related information

[0034] Census transform is a non-parametric transform that uses image neighborhood information, which can represent the local texture features of the image. The Census algorithm generally uses a rectangular window to traverse the image, and compares the relative size of the gray value of the neighboring pixels and the center pixel in the window. When the gray value is less than or equal to the center pixel, it is recorded as 0, and when the gray value is greater than the center pixel, it is recorded as 1. Finally, these values ​​are connected bit by bit into the Hamming distance, as the characteristic value that characterizes the characteristics of the central pixel, and the distance vector string in the neighborhood can be used to retain the local texture structure information of the image. Then the Census transformation ...

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 the field of binocular stereo imaging, and provides a matching cost algorithm with high precision and strong anti-interference capability in order to improve the performance of a Census algorithm under the condition of repeated texture and discontinuity of parallax. Therefore, the technical scheme adopted by the invention is as follows: based on neighborhood related information, as for two to-be-matched input pictures, taking the left view as a reference, taking a window with n * n pixels; calculating the Census transformation matching cost of the model; and taking ann * n window in the right view, moving the window from left to right and from top to bottom, respectively recording values of matching costs of the window, selecting a point with the minimum matchingcost as a matching point of the left image, traversing each point in the left image according to the method, and respectively finding out the corresponding matching point of the point in the right image, thereby completing matching of the left view and the right view. The method is mainly applied to three-dimensional imaging processing occasions.

Description

technical field [0001] The invention relates to the field of binocular stereo imaging, in particular to the core algorithm of stereo matching. The accuracy and robustness of the matching algorithm are improved by combining the Census algorithm based on neighborhood-related information with the AD algorithm. Background technique [0002] Stereo vision technology has been widely used in the fields of virtual reality, three-dimensional measurement, stereo camera, object recognition and robot navigation. Among them, stereo matching is a key technology of stereo vision. Its algorithm has high complexity and needs to process a large amount of data. At present, there is no general algorithm that can meet the requirements of most scenes. [0003] Among many matching algorithms, the AD algorithm is based on the gray value of the pixel, that is, it is assumed that the same feature point of the two images has the same gray value, but the actual situation often does not meet this condi...

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): G06T7/13G06T7/593G06T7/80
CPCG06T7/13G06T7/593G06T7/85G06T2207/20221G06T2207/10012
Inventor 高静张培文徐江涛史再峰
Owner TIANJIN 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