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

A multi-temporal point cloud automatic registration method based on shape-invariant features

An automatic registration and multi-temporal technology, applied in image analysis, instrumentation, computing, etc., can solve the problems of large point cloud changes, low registration efficiency, and poor accuracy, and achieve efficient automatic registration and high stability registration Effect

Active Publication Date: 2021-03-02
CHINA UNIV OF MINING & TECH (BEIJING)
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0019] The technical problem to be solved by the present invention is to design a point cloud automatic fine registration method for complex changing scenes in view of the problems of large change range, low registration efficiency and poor accuracy of point clouds in multi-period changing fields

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 multi-temporal point cloud automatic registration method based on shape-invariant features
  • A multi-temporal point cloud automatic registration method based on shape-invariant features
  • A multi-temporal point cloud automatic registration method based on shape-invariant features

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0043] by figure 2 , image 3 and Figure 4 As an example, the rough registration method of changing scene point clouds based on shape-invariant points is described in detail. The dots in the figure represent the positions of congruent four-point pairs, the triangles represent the four-point-based neighborhood points, and the lines between the points represent Feature matching correspondence. Its specific implementation is as follows:

[0044] Step 1: If figure 2 As shown, using the affine invariant constraints to find four congruent pairs of the reference point cloud P and the point cloud to be registered Q: Aiming at the construction of four coplanar points in P, under the constraint of formula (1), the i-th iteration of the 4PCS algorithm starts from the reference Randomly find three points in the point cloud to form a plane, denoted as (p 1i ,p 2i ,p 3i ), calculate the coordinate p of the fourth point satisfying the condition according to formula (2) 4i , formin...

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

This patent discloses a multi-temporal point cloud automatic registration method based on shape-invariant features: aiming at the point cloud registration characteristics of multi-temporal changing scenes, the point cloud rough registration is completed through shape-invariant point extraction and matching, and then the multi-temporal point cloud is searched The shape-invariant region in the phase point cloud estimates the rotation and translation parameters between multi-temporal point clouds, and completes the point cloud fine registration. Specifically, for point cloud coarse registration, firstly determine the four-point pairs with approximately the same name in the multi-temporal point cloud, and then calculate the feature descriptors of the points in the neighborhood centered on the four-point pairs, and determine the multi-temporal point cloud through feature matching and spatial geometric constraints Matching point sets with the same name between them, based on which the rotation and translation parameters are estimated, and the rough registration of the point cloud is completed; in the fine registration stage, this patent adopts an iterative strategy to extract the shape-invariant region in the multi-temporal point cloud, and further optimizes the rough registration accordingly. The initial rotation and translation parameters obtained in the quasi-phase, and finally the optimized parameters are used for the rigid transformation of the whole point cloud, and the automatic registration of the multi-temporal point cloud is completed.

Description

technical field [0001] The invention relates to the technical field of spatial information applications, in particular to a three-dimensional point cloud fine registration method for changing scenes. Background technique [0002] In recent years, research on point cloud registration has received extensive attention. The mainstream point cloud acquisition methods can be divided into two types: one is to use laser scanning technology to actively emit electromagnetic waves, and obtain the three-dimensional information of the measured target by means of distance measurement and angle measurement; the other is to use image reconstruction technology, through multi-view The three-dimensional information of the photographed object is restored by means of image matching and aberration optimization. Studies have shown that 3D measurement technology has been widely used in the fields of cultural relics protection, topographic surveying and mapping, forestry production estimation, mine...

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 Patents(China)
IPC IPC(8): G06T7/33
Inventor 许志华徐二帅吴立新
Owner CHINA UNIV OF MINING & TECH (BEIJING)
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