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

Three-dimensional point cloud registration method adopting CPD (coherent point drift) algorithm based on affine transformation model

An affine transformation model, three-dimensional point cloud technology, applied in computing, image data processing, instruments, etc., can solve the problems of low registration accuracy, long program running time, poor robustness, etc., to achieve high registration accuracy, shorten the operation time effect of time

Active Publication Date: 2017-09-26
HARBIN INST OF TECH
View PDF3 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problems of the existing mainstream 3D point cloud registration algorithm CPD with high algorithm complexity, long program running time, low registration accuracy, and poor robustness, and propose a 3D point cloud based on affine transformation model CPD algorithm. Point cloud registration method

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
  • Three-dimensional point cloud registration method adopting CPD (coherent point drift) algorithm based on affine transformation model
  • Three-dimensional point cloud registration method adopting CPD (coherent point drift) algorithm based on affine transformation model
  • Three-dimensional point cloud registration method adopting CPD (coherent point drift) algorithm based on affine transformation model

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0021] Specific implementation mode one: combine figure 1 Describe this specific embodiment, the three-dimensional point cloud registration method based on the affine transformation model CPD algorithm of this embodiment, specifically implement according to the following steps:

[0022] Step 1. Use the image acquisition device in the painting robot to scan the object to be painted, and collect a set of three-dimensional point cloud data as the point cloud to be registered; figure 2 ;

[0023] Step 2. Preprocess the point cloud to be registered collected in step 1, and use the obtained point cloud data as a reference point set; image 3 ;

[0024] Step 3. Calculate the covariance σ between the reference point set and the corresponding saved template point set obtained in step 2 2 , and initialize the affine transformation matrix B and translation vector t;

[0025] Step 4. According to the σ obtained in Step 3 2 , B, t three parameters and the template point set and refer...

specific Embodiment approach 2

[0028] Specific embodiment 2: The difference between this embodiment and specific embodiment 1 is that in the step 2, the point cloud to be registered obtained in the step 1 is preprocessed, and the obtained point cloud data is used as a reference point set; the specific process is :

[0029] Step 21, delete the background point cloud data that does not need to be registered in the point cloud to be registered collected in step 1, and obtain the point cloud after removing the background;

[0030] Step 22, using the statistical filter and the radius filter to delete the outlier points in the point cloud after removing the background obtained in step 21, to obtain the filtered point cloud;

[0031] Step two and three, down-sampling the filtered point cloud obtained in step two or two, to obtain the down-sampled point cloud; with sparse point cloud data, the purpose of reducing the amount of point cloud data is achieved;

[0032] Step 24: Save the down-sampled point cloud obtain...

specific Embodiment approach 3

[0034] Specific embodiment three: the difference between this embodiment and specific embodiment one or two is: the covariance σ of the reference point set and the corresponding saved template point set is obtained in the calculation step two in the step three 2 , and initialize the affine transformation matrix B and the translation vector t; the specific process is:

[0035] Step 31. Calculating the reference point set X N×D =(x 1 ,...x N ) T and template point set Y M×D =(y 1 ,...y M ) T The covariance of :

[0036]

[0037] Among them, M and N are the number of points in the reference point set and the template point set respectively, and the value is a positive integer; D is the dimension of the point set, x n is the D-dimensional vector of the nth point in the reference point set, y m is the D-dimensional vector of the mth point in the template point set;

[0038] Step 32, initialize the affine transformation matrix B and the translation vector t, the affine ...

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 provides a three-dimensional point cloud registration method adopting a CPD (coherent point drift) algorithm based on an affine transformation model, relates to a spraying robot position registration method based on point cloud registration and aims to solve the problems of high complexity, long program running time, low registration accuracy and poor robustness of the conventional mainstream three-dimensional point cloud registration algorithm CPD. The specific process comprises the following steps: 1, obtaining a group of three-dimensional point cloud data to serve as to-be-registered point cloud; 2, taking the obtained point cloud data as a reference point set; 3, calculating a covariance and initiating B and t; 4, parallelly computing P by a GPU; 5, solving parameters B, t and sigma<2> when an objective function gets maximum; 6, iterating steps 4 and 5 repeatedly until the covariance is smaller than a set threshold, solving B and t as well as a finally registered result point set when the covariance is smaller than the set threshold, and performing spraying on a to-be-sprayed object according to the final registration result. The three-dimensional point cloud registration method applies to the field of spraying by spraying robots.

Description

technical field [0001] The invention relates to a position registration method for a painting robot based on point cloud registration. Background technique [0002] With the rapid development of data acquisition technology and computer technology, people can more conveniently use various 3D data acquisition equipment to obtain a series of sampling points on the surface of the object model, that is, 3D point cloud data, and the corresponding point cloud data processing technology has also been recognized. widely used. As one of the key technologies in point cloud data processing technology, 3D point cloud registration technology is widely used in industrial product inspection, medical diagnosis, archaeology because of its significant advantages in flexibility, portability, cost and accuracy. In many fields such as research and architectural design, especially in the field of painting robots, the use of 3D point cloud registration technology can greatly improve the efficiency...

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): G06T7/33
CPCG06T7/344G06T2207/10028
Inventor 高会军滕军李湛林伟阳
Owner HARBIN INST OF 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