Fast three-dimensional point cloud searching and matching method

A technology of 3D point cloud and matching method, applied in image data processing, instrumentation, calculation, etc., can solve the problems of registration failure, iterative local minimization, mismatching, etc., and achieve the effect of improving work efficiency and strong fault tolerance.

Inactive Publication Date: 2010-09-29
BEIHANG UNIV
View PDF1 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If there are similar structures in the scene, iterations tend to fall into local minima, and mismatches occur, which leads to the failure of the entire registration

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
  • Fast three-dimensional point cloud searching and matching method
  • Fast three-dimensional point cloud searching and matching method
  • Fast three-dimensional point cloud searching and matching method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Such as figure 1 As shown, the present invention includes the following calculation steps: main axis registration, measurement axis generation, low-precision search, high-precision search and one iteration result generation. The main axis registration link is responsible for defining the direction of the point cloud and completing the initial registration; the measurement axis generation link provides the search range in the current iteration for the moving point cloud; The best registration pose; the high-precision search is responsible for obtaining a better best registration pose with a smaller step size search position error on the basis of the low-precision search; the generation of an iterative result is responsible for generating an iteration based on the measurement results at each position The final result of the iteration. Specific steps are as follows:

[0028] There are two point clouds P and X to be registered, such as figure 2 shown. P is the moving p...

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 relates to a fast three-dimensional point cloud searching and matching method, which comprises the steps of main shaft registration, measuring shaft generation, low-precision searching, high-precision searching and primary iteration result generation. The main shaft registration link is responsible for the defining point cloud direction and completes the initial registration, the measuring shaft generation link provides the searching range in the current iteration for moving point clouds, the low-precision searching adopts an ergodic method for looking for the optimal registration posture of the moving point clouds on the current measuring shaft, the high-precision searching is responsible for obtaining better optimal registration posture at smaller step length searching position errors on the basis of the low-precision searching, and the primary iteration result generation link is responsible for generating the final results of the primary iteration according to the measuring results in each position. The invention starts from the geometrical shape of the point clouds, and completes the ergodic searching at different precisions through the mutual movement and rotation between two point clouds to find the optimal matching position, the algorithm has good fault-tolerance performance, and the invention is suitable for any three-dimensional digital instrument to obtain the searching matching of the three-dimensional point clouds.

Description

technical field [0001] The invention relates to a fast three-dimensional point cloud search and matching method, which belongs to the technology of remote sensing and surveying and mapping, computer vision and pattern recognition, and is applicable to three-dimensional point cloud data obtained by any three-dimensional digitizer. Background technique [0002] 3D point cloud registration has always been an issue of great concern in the fields of computer vision and pattern recognition, remote sensing and surveying and mapping. Most of the existing registration methods are based on the ICP algorithm to iteratively find the closest point between two point clouds, so as to achieve point cloud registration. If there are similar structures in the scene, iterations tend to fall into local minima, and mismatches occur, which leads to the failure of the entire registration. Contents of the invention [0003] The technology of the present invention solves the problem: overcomes the...

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): G06T7/00
Inventor 胡少兴张爱武刘思诚朱林林
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap