Check patentability & draft patents in minutes with Patsnap Eureka AI!

Point cloud registration method for voting by using plane shape and topological graph

A technology of plane shape and point cloud registration, applied in the field of remote sensing mapping, to achieve the effect of stable features, improved robustness and less noise impact

Pending Publication Date: 2022-05-10
WUHAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main technical problem to be solved by the present invention is to design an accurate and robust descriptor for plane features to match planes with the same name and then solve the problem of large data point cloud registration in urban scenes

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
  • Point cloud registration method for voting by using plane shape and topological graph
  • Point cloud registration method for voting by using plane shape and topological graph
  • Point cloud registration method for voting by using plane shape and topological graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The technical solutions of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0056] Three steps are the most critical in plane-based registration methods:

[0057] (1) How to extract the plane quickly and accurately. In the current plane-based registration, most of the planes in the scene are extracted by RANSAC or a variant of RANSAC. It is not suitable for the point cloud plane segmentation task of the scene. Other plane segmentation methods such as region growing and Hough transform and other point-based segmentation algorithms can also be used for plane segmentation, but their efficiency is difficult to meet the requirements of large scene plane segmentation, and there is an over-segmentation phenomenon that affects the accuracy of plane parameter calculation. . The voxel-based plane segmentation algorithm can efficiently complete the task of plane segmentation of large scene point clouds, but it w...

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 point cloud registration method for voting by using a plane shape and a topological graph, which comprises the following steps of: 1, roughly segmenting a point cloud into plane primitives by using a voxelization point cloud plane segmentation algorithm, and calculating accurate plane parameters by using an RANSAC plane fitting method; 2, selecting a plane shape as a characteristic of plane matching, and designing a plane shape descriptor to perform homonymous plane matching; step 3, constructing a topological graph according to the matched homonymous plane positions and the normal vector included angle relationship, and based on a homonymous plane edge voting strategy, rejecting wrongly matched planes; and step 4, selecting several groups of optimal homonymous planes to calculate a transformation matrix of the point clouds of the two sites so as to complete registration of the point clouds. The HIA-TCD plane shape descriptor is designed, the descriptor considers holes in the plane and the phenomenon of partial shielding in the scanning process, and the robustness of plane matching can be improved.

Description

technical field [0001] The invention relates to a point cloud automatic rough registration algorithm based on plane shape matching and topology map voting, and the algorithm belongs to the field of remote sensing surveying and mapping. Background technique [0002] In recent years, with the development of 3D Lidar technology, point clouds have been widely used in urban scenes, such as 3D reconstruction of buildings, urban planning, indoor navigation, etc., and point clouds have proved to be the most suitable data source for drawing urban scenes. one. Limited by the scanning distance and scanning method of 3D laser scanners, it is usually impossible to obtain complete scene data after one-station scanning. It is necessary to improve data integrity and quality through multi-angle, multi-platform, multi-station, and multi-time equal methods. The point clouds need to be unified into the same coordinate system through registration technology, so point cloud registration plays an...

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): G06T7/33G06T19/20
CPCG06T7/33G06T19/20G06T2207/10028
Inventor 谢洪闫利韦朋成陈长军李瑶戴集成
Owner WUHAN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com