Low-overlapping-rate three-dimensional point cloud registration method

A technology of 3D point cloud and overlapping rate, applied in image data processing, instrumentation, 3D modeling, etc., can solve the problems of difficulty and low precision in the registration of two point clouds

Active Publication Date: 2020-12-29
ZHONGBEI UNIV
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of high difficulty and low precision in registration of two point clouds with low overlap rate, the present invention provides a 3D point cloud registration method with low overlap rate

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
  • Low-overlapping-rate three-dimensional point cloud registration method
  • Low-overlapping-rate three-dimensional point cloud registration method
  • Low-overlapping-rate three-dimensional point cloud registration method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] Such as figure 1 As shown, a low overlap rate 3D point cloud registration method includes the following steps:

[0065] Step 1, construct multi-scale descriptors based on curvature features and normal vectors;

[0066] Step 1.1, for each query point P in each neighborhood radius r l Build the covariance matrix,

[0067]

[0068] Among them, the scale l=1,...,L; the neighborhood radius corresponding to the scale is expressed as r 1 2 L , S l Indicates that the distance from the query point P is within the neighborhood radius r l The set S of points in the range l ={P i |||P i -P||≤r l};

[0069] Step 1.2, use the singular value decomposition algorithm SVD decomposition formula (1) to obtain three eigenvalues ​​λ l1 ≥λ l2 ≥λ l3 and its corresponding eigenvector n l1 , n l2 , n l3 , the eigenvector n corresponding to the smallest eigenvalue l3 That is, the normal vector of the plane, denoted as n l ;Set the direction of the normal vector of the area to ...

Embodiment 2

[0108] The data comes from the 3D point cloud model published by Stanford University and the entity 3D scanning data from the geometryhub website. The environment is a 64-bit operating system of Windows 10 and a development platform of MATLAB 2018b.

[0109] When the overlap rate of the source point cloud and the target point cloud is lower than 60%, the degree of overlap of the two point clouds is low, and when their overlap rate is higher than 60%, the degree of overlap is high. In order to prove the effectiveness of the method proposed by the present invention, it is divided into two cases with high overlap rate and low overlap rate.

[0110] For the point cloud model, the point cloud data acquired under different viewing angles are used to reflect their overlapping ratio. Select several representative sets of data for the results display. Point cloud data with high overlap rate: Bunny000, Bunny045 and Dragon000, Dragon024 two sets of point cloud data, they have obvious o...

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 low-overlapping-rate three-dimensional point cloud registration method, and belongs to the technical field of machine vision. The method aims at solving the problems of highregistration difficulty, low precision and the like of two point clouds with low overlapping rate. The method comprises the following steps: firstly, establishing a multi-scale descriptor by utilizingcurvature characteristics of point cloud to ensure that point cloud data is complete and redundant data is minimum; secondly, performing corresponding relation clustering partitioning by utilizing the angle difference of the multi-scale descriptors to obtain an overlapping region of the source point cloud and the target point cloud; and finally, substituting the point clouds of the overlapping region and the corresponding relationship of the point clouds into a convex optimization problem, removing outliers and optimizing the corresponding relationship, realizing coarse registration, and refining by utilizing an ICP algorithm. According to the invention, the useful search range of point cloud registration can be reduced, the registration calculation amount is reduced, and more advantageous registration precision and time efficiency are provided for point cloud data with a low initial overlapping degree. The method can be widely applied to the fields of three-dimensional model reconstruction, cultural heritage management, robot navigation and positioning and the like.

Description

technical field [0001] The invention belongs to the technical field of machine vision, and in particular relates to a three-dimensional point cloud registration method with a low overlap rate. Background technique [0002] In recent years, 3D point cloud data has been widely used in 3D model reconstruction, cultural heritage management, robot navigation and positioning and other fields. Fast and accurate 3D point cloud registration technology is the key technology and research focus. The goal of 3D point cloud registration is to find the optimal rigid body transformation that aligns two input point clouds to a common coordinate system. In practical applications, the data may be heavily occluded, and the overlapping area between two point clouds is small, which makes the process of finding the optimal rigid body transformation challenging. Therefore, finding fast, accurate, and robust registration algorithms for point clouds with smaller overlapping ranges is an active rese...

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): G06T7/33G06T17/00G06K9/62
CPCG06T7/33G06T17/00G06T2207/10028G06F18/23
Inventor 张元李晓燕韩燮
Owner ZHONGBEI 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