Multi-view three-dimensional data registration method based on spatial line recognition and matching

A three-dimensional data, multi-view technology, applied in the field of multi-view three-dimensional data splicing, can solve problems such as time-consuming, inability to achieve alignment, cumbersome measurement process, etc., to prevent convergence errors and reduce the amount of calculation.

Active Publication Date: 2013-03-13
BEIHANG UNIV
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The method based on pasting markers on the surface of the model can provide higher splicing accuracy, but the measurement process is cumbersome due to the need to paste markers on the surface, and some models cannot be touched during measurement, which limits the application of the method
However, the splicing method based on point cloud data needs to iteratively search for corresponding point pairs and adjust the relative posture during the execution process, which consumes a lot of time, and tends to converge to the local extremum during the operation process, so that the alignment cannot be achieved.

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
  • Multi-view three-dimensional data registration method based on spatial line recognition and matching
  • Multi-view three-dimensional data registration method based on spatial line recognition and matching
  • Multi-view three-dimensional data registration method based on spatial line recognition and matching

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0059] Specific implementation method: as follows figure 1 The shown method steps describe a concrete implementation.

[0060] The present invention is a multi-view three-dimensional data splicing method based on spatial straight line recognition and matching. The specific steps of the method are:

[0061] Step 1: Extract straight line feature parameters from the original point cloud data: first find the point cloud that belongs to the line feature according to the curvature of the point cloud data, assuming that the point cloud set can be used P{(x 1 ,y 1 ,z 1 )...(x n ,y n ,z n )}express, is the mean value of the coordinates, and the matrix can be constructed from the mean value Then the covariance matrix of P:

[0062] X=[P-N] T ·[P-N]

[0063] According to the characteristics of eigenvalues ​​and eigenvectors, we can know that:

[0064] X·α=λ·α, let λ 1 ,λ 2 ,λ 3 is the eigenvalue of X, and the size relationship has λ 1 2 3 , then the estimated curvature i...

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 discloses a multi-view three-dimensional data registration method based on spatial line recognition and matching. The multi-view three-dimensional data registration method based on the spatial line recognition and matching is suitable for multi-view registration on data with obvious edge features. The multi-view three-dimensional data registration method based on the spatial line recognition and matching comprises the following main steps of: extracting line segments from three-dimensional point cloud data; realizing the matching of common line segments under different views according to the inherent constrained relationship of positions and angles of the extracted line segments; finding rotation invariant corresponding points under different views on the basis of the line segment matching; and obtaining an optimal global attitude transformation matrix based on the corresponding points to realize multi-view three-dimensional data registration.

Description

technical field [0001] The invention relates to a multi-view three-dimensional data splicing method based on spatial straight line recognition and matching, which is a method for spatial three-dimensional point cloud data processing, and specifically relates to a multi-view three-dimensional data splicing method, which belongs to three-dimensional measurement and computer vision technology field. Background technique [0002] In 3D measurement, it is often necessary to obtain the overall 3D shape model of the workpiece. Due to the limitation of single viewing angle measurement, it is necessary to stitch together the measurement results of multiple viewing angles to obtain the overall shape data, so the selection of stitching method is more critical. [0003] In order to realize the splicing of multi-view point clouds, the common method is to paste marker points on the surface of the measurement object, determine the transformation matrix between different perspectives by ide...

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): G06F17/10
Inventor 李旭东赵慧洁李伟姜宏志
Owner BEIHANG 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