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

3D color point cloud registration method based on global optimization and multi-constraint condition iteration

A global optimization, color point cloud technology, applied in computer parts, image data processing, instruments, etc., can solve the problems of long registration time and low registration accuracy

Active Publication Date: 2020-08-21
XI'AN POLYTECHNIC UNIVERSITY
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a 3D color point cloud registration method with global optimization and multi-constraint iteration, which solves the problems of low registration accuracy and long registration time in existing 3D color point cloud registration methods

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
  • 3D color point cloud registration method based on global optimization and multi-constraint condition iteration
  • 3D color point cloud registration method based on global optimization and multi-constraint condition iteration
  • 3D color point cloud registration method based on global optimization and multi-constraint condition iteration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0129] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0130] The present invention is a 3D color point cloud registration method with global optimization and multi-constraint condition iteration, such as figure 1 As shown, the specific steps are as follows:

[0131] Step 1, using marker-based multi-state outliers to eliminate noise, outliers and outlier clusters in the original point cloud data; specifically follow the steps below:

[0132] Step 1.1, use the k-d tree to search the neighborhood of the point cloud;

[0133] Step 1.2, after step 1.1, calculate the point cloud normal vector with the local surface fitting method of moving least squares method;

[0134] Step 1.3, after step 1.2, set different thresholds for different point cloud data, compare the ratio of the orthogonal component of point normal difference with the set threshold, and mark outliers as the judgment conditions of isola...

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 3D color point cloud registration method based on global optimization and multi-constraint condition iteration. The method comprises: firstly, effectively eliminating noise,outliers and outlier clusters by adopting a multi-state outlier algorithm based on marks; secondly, using a PSO algorithm for carrying out preliminary coarse registration processing; thirdly, using anant colony optimization algorithm to carry out global optimization processing; and finally, using a global multi-constraint condition iterative closest point precise registration algorithm to carry out precise registration processing. In the coarse registration process, the result is globally optimized by using an ant colony optimization algorithm, so that error pairing of coarse registration isreduced, the coarse registration precision is improved, an initial value with higher precision is initialized for subsequent fine registration processing, and the whole registration time is further shortened; in the fine registration process, ICP iterative fine registration processing is carried out by adopting Euclidean distance and curvature double constraint conditions between corresponding points, so that the registration precision is improved to a certain extent.

Description

technical field [0001] The invention belongs to the technical field of 3D point cloud data processing, and in particular relates to a 3D color point cloud registration method with global optimization and multi-constraint condition iteration. Background technique [0002] With the development of artificial intelligence, image registration technology has gradually transitioned from two-dimensional images to three-dimensional images, and 3D point cloud, as one of the typical representatives of three-dimensional images, has gradually been widely used. 3D point cloud registration is to first use the computer to preprocess the 3D point cloud, then use a suitable algorithm to perform rough registration on the processed data, and finally select a suitable method to perform fine registration on the results of the rough registration. In the whole process of point cloud data registration, the selection of filters, coarse registration criteria and fine registration constraints directly ...

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): G06T7/33G06K9/62G06N3/00
CPCG06T7/337G06N3/006G06T2207/10024G06T2207/10028G06T2207/20016G06F18/232G06F18/2433Y02P90/30
Inventor 任小玲陈逍遥郭晓蓉
Owner XI'AN POLYTECHNIC UNIVERSITY
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