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

Automatic Matching Method of Public Landmarks Based on Dynamic Hierarchy

A marker point and dynamic technology, applied in the field of computer vision, can solve the problems of large calculation, difficult calculation speed and stitching accuracy to meet industrial production requirements, and achieves speed and accuracy problems, low matching error rate, and reduced matching error rate. Effect

Active Publication Date: 2017-02-15
CHANGCHUN UNIV OF SCI & TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method needs to calculate the distance of a large number of useless marker points, and at the same time, it will generate many wrong point pairs. Its calculation speed and splicing accuracy are also difficult to meet the actual industrial production needs.

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
  • Automatic Matching Method of Public Landmarks Based on Dynamic Hierarchy
  • Automatic Matching Method of Public Landmarks Based on Dynamic Hierarchy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Below in conjunction with accompanying drawing, the present invention will be further described: as figure 1 As shown, the automatic matching method of public landmarks based on dynamic layering is characterized in that: the three-dimensional scanner 1 is connected to the computer 2 through a cable, and the outer surface of the object 3 to be measured is marked with landmarks. The specific method is as follows accomplish:

[0021] Step 1. Let the set of marker points of the object 3 to be measured obtained by the 3D scanner 1 and the computer 2 at the viewpoint 1 be P; under the condition that the parameters of the 3D scanner 1 remain unchanged, the 3D scanner 1 at the viewpoint The set of marker points of the object 3 to be measured obtained at 2 is denoted by Q, the number of common marker points in P and Q is N, N≥3, and n is set to 3.

[0022] Step 2. Search for n marker points with the smallest X-axis coordinate value in P. The set P_Min_x is composed of n marker ...

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 present invention relates to a kind of public sign point automatic matching method based on dynamic layering, it is characterized in that: its specific method is realized by the following steps: suppose the set of sign points of the object to be measured obtained by the three-dimensional scanner and the computer at the viewpoint is P; search for n marker points with the smallest X-axis coordinate value in P, search for n marker points with the smallest X-axis coordinate value in Q, construct four dynamic distance matrices of Q, and put them in the four dynamic distance matrices of P The element values ​​of the element value of Q and the element values ​​in the four dynamic distance matrices of Q are judged to be equal, the set E' is formed by all the marker points in E, and the set F' is formed by all the marker points in F; if the marker points A to E' The Euclidean distances of all marker points are equal to the Euclidean distances of all corresponding marker points among marker points B to F'. It effectively reduces the matching error rate; and also solves the speed and precision problems faced by traditional matching markers.

Description

technical field [0001] The invention relates to an automatic matching method of public marker points based on dynamic layering, which belongs to the technical field of computer vision. Background technique [0002] Three-dimensional reconstruction is a technology that simulates, recognizes, and analyzes objects by computer to create a corresponding model to create a virtual scene. It models by measuring the three-dimensional information of each position of the object. Due to the size and three-dimensional structure of the object, the projector cannot obtain the complete three-dimensional information of the object at one time, and it is necessary to build an overall model through point cloud stitching after multiple measurements. Point cloud splicing is to unify the point cloud information of different parts into one coordinate system through coordinate transformation. The key lies in the quick matching of feature points or marker points. [0003] The current point cloud sti...

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 Patents(China)
IPC IPC(8): G06T15/00
Inventor 韩成张超权巍蒋振刚薛耀红杨华民冯欣范静涛丁莹赵义武杨帆白宝兴
Owner CHANGCHUN UNIV OF SCI & 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