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

A parallel three-dimensional point cloud data automatic registration method

A 3D point cloud and data technology, applied in image data processing, instruments, calculations, etc., can solve the problems of affecting the registration effect, huge time cost, and high accuracy requirements of artificial standards, so as to reduce computational complexity and improve accuracy , to avoid the effect of misregistration

Active Publication Date: 2019-04-02
NORTHEASTERN UNIV
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Manual registration needs to manually mark multiple corresponding points in the two point cloud data in advance, and then solve the homogeneous equation of rigid transformation according to the marked corresponding points to solve the rotation matrix R and translation vector T. Finally, according to the obtained R and T, the The coordinate systems of the two point clouds are unified. This method has extremely high requirements on the accuracy of the artificial standard, and the wrong standard corresponding point will affect the registration effect.
Automatic registration calculates the feature descriptor FPFH of the point cloud data, and performs feature matching, replaces the manual standard by feature matching, and then solves the rotation and translation matrix. This method requires a lot of preprocessing of the point cloud data. In the data, the extraction and matching of features require huge time costs, and the accuracy of feature matching is the key to the registration results

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
  • A parallel three-dimensional point cloud data automatic registration method
  • A parallel three-dimensional point cloud data automatic registration method
  • A parallel three-dimensional point cloud data automatic registration method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention provides a parallel automatic registration method for 3D point cloud data, such as Figure 4 shown, including the following steps:

[0037] Step 1: Obtain the source point cloud P and target point cloud Q to be registered under different views;

[0038] Step 2: Point cloud downsampling processing. The downsampling process is performed on large-scale 3D point cloud data to reduce the amount of calculation while retaining the characteristics of the point cloud data to the greatest extent. Here, the scale-invariant feature transformation 3D-SIFT is used to extract the key points in the point cloud as the result of downsampling. In particular, for the field of 3D reconstruction, the sparse point cloud can be directly used as the downsampling result. The number of key points N in the source point cloud P after downsampling p , the number of key points M in the target point cloud Q q .

[0039] Step 3: Calculate the normal vector for the points in ...

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 parallel three-dimensional point cloud data automatic registration method. The method comprises the steps of obtaining two to-be-registered point clouds which are in different views and have overlapped regions; downsampling processing is carried out on the point cloud to reduce the calculation amount; calculating a normal vector of the point cloud data and calculating a fast point feature histogram FPFH feature; starting a plurality of processes to select n points from one point cloud and search corresponding points from the other point cloud, calculating a rotation translation matrix of rigid transformation according to the corresponding points, calculating an error measurement standard, taking a result of the minimum error measurement standard as an iteration result of this time, carrying out iteration for multiple times, and taking a final result as a transformation matrix; and finally, performing fine registration by using an ICP iteration algorithm.

Description

technical field [0001] The invention belongs to the field of point cloud data processing, in particular to a parallel automatic registration method for three-dimensional point cloud data. Background technique [0002] 3D point cloud data is a collection of point data on the appearance surface of objects obtained by measuring instruments, and is a digital representation of the real world. 3D point cloud data has strong application value in building protection, 3D maps, biomedicine and other fields. 3D point cloud data will encounter the problem of unifying the point cloud data acquired by two different views into the same coordinate system, that is, point cloud registration. [0003] The current point cloud registration technology is mainly divided into manual registration and automatic registration. Manual registration needs to manually mark multiple corresponding points in the two point cloud data in advance, and then solve the homogeneous equation of rigid transformation...

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): G06T7/33
CPCG06T7/33G06T2207/10028
Inventor 杨晓春王斌冯策
Owner NORTHEASTERN UNIV
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